Hugging Face's logo

farama-minari
/
Ant-v5-SAC-simple

Reinforcement Learning
stable-baselines3
Ant-v5
deep-reinforcement-learning
Eval Results
Model card Files Community
Kallinteris-Andreas commited on
Commit
6673f33
·
verified ·
1 Parent(s): 04c09ad

model

Browse files
Files changed (12) hide show
  1. README.md +1 -1
  2. ant-v5-sac-simple.zip +2 -2
  3. ant-v5-sac-simple/actor.optimizer.pth +1 -1
  4. ant-v5-sac-simple/critic.optimizer.pth +1 -1
  5. ant-v5-sac-simple/data +25 -25
  6. ant-v5-sac-simple/ent_coef_optimizer.pth +1 -1
  7. ant-v5-sac-simple/policy.pth +1 -1
  8. ant-v5-sac-simple/pytorch_variables.pth +1 -1
  9. ant-v5-sac-simple/system_info.txt +1 -1
  10. config.json +1 -1
  11. replay.mp4 +2 -2
  12. results.json +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: Ant-v5
17
  metrics:
18
  - type: mean_reward
19
- value: 531.54 +/- 55.28
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: Ant-v5
17
  metrics:
18
  - type: mean_reward
19
+ value: 1677.84 +/- 848.55
20
  name: mean_reward
21
  verified: false
22
  ---
ant-v5-sac-simple.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239b076dabdd4f586b1a9639a5bbe07f994de3857f65ac946fad78ddde8f46d7
3
- size 4275837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28a820d3f012f3daf2eda6e5c7c37e7dca430afa8b3dcc09f16276fbefc04d2
3
+ size 4275877
ant-v5-sac-simple/actor.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:607fac6410a7458acd4494acd6ae98b5279fd0035c37c583c7bd569994833e45
3
  size 783182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f873fe42573193e951c90cd069af5ff9b11dc32a0572f32916d413e16990d1ea
3
  size 783182
ant-v5-sac-simple/critic.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab25c1dc5b0647e348955ad81fee700fc6880e4552ab2c71318652339eb4b203
3
  size 1533866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bacdcd3d856f50ec3c78e9ac6f04d023dbeb72a8c2a1591a56952e287c581384
3
  size 1533866
ant-v5-sac-simple/data CHANGED
@@ -5,33 +5,33 @@
5
  "__module__": "stable_baselines3.sac.policies",
6
  "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
7
  "__doc__": "\n Policy class (with both actor and critic) for SAC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
8
- "__init__": "<function SACPolicy.__init__ at 0x7f142000c400>",
9
- "_build": "<function SACPolicy._build at 0x7f142000ca40>",
10
- "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f142000cae0>",
11
- "reset_noise": "<function SACPolicy.reset_noise at 0x7f142000cb80>",
12
- "make_actor": "<function SACPolicy.make_actor at 0x7f142000cc20>",
13
- "make_critic": "<function SACPolicy.make_critic at 0x7f142000ccc0>",
14
- "forward": "<function SACPolicy.forward at 0x7f142000cd60>",
15
- "_predict": "<function SACPolicy._predict at 0x7f142000ce00>",
16
- "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f142000cea0>",
17
  "__abstractmethods__": "frozenset()",
18
- "_abc_impl": "<_abc._abc_data object at 0x7f142001c300>"
19
  },
20
  "verbose": 0,
21
  "policy_kwargs": {
22
  "use_sde": false
23
  },
24
- "num_timesteps": 100000,
25
- "_total_timesteps": 100000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": 0,
28
  "action_noise": null,
29
- "start_time": 1729211451595343246,
30
  "learning_rate": 0.0003,
31
- "tensorboard_log": "runs/z50t0ova",
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
- ":serialized:": "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"
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
@@ -39,22 +39,22 @@
39
  },
40
  "_last_original_obs": {
41
  ":type:": "<class 'numpy.ndarray'>",
42
- ":serialized:": "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"
43
  },
44
- "_episode_num": 232,
45
  "use_sde": false,
46
  "sde_sample_freq": -1,
47
  "_current_progress_remaining": 0.0,
48
  "_stats_window_size": 100,
49
  "ep_info_buffer": {
50
  ":type:": "<class 'collections.deque'>",
51
- ":serialized:": "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"
52
  },
53
  "ep_success_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
56
  },
57
- "_n_updates": 18000,
58
  "buffer_size": 1000000,
59
  "batch_size": 256,
60
  "learning_starts": 10000,
@@ -68,13 +68,13 @@
68
  "__module__": "stable_baselines3.common.buffers",
69
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
70
  "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
71
- "__init__": "<function ReplayBuffer.__init__ at 0x7f142af04c20>",
72
- "add": "<function ReplayBuffer.add at 0x7f142af04d60>",
73
- "sample": "<function ReplayBuffer.sample at 0x7f142af04e00>",
74
- "_get_samples": "<function ReplayBuffer._get_samples at 0x7f142af04ea0>",
75
- "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f142af04f40>)>",
76
  "__abstractmethods__": "frozenset()",
77
- "_abc_impl": "<_abc._abc_data object at 0x7f1430da9f00>"
78
  },
79
  "replay_buffer_kwargs": {},
80
  "train_freq": {
 
5
  "__module__": "stable_baselines3.sac.policies",
6
  "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
7
  "__doc__": "\n Policy class (with both actor and critic) for SAC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
8
+ "__init__": "<function SACPolicy.__init__ at 0x7f3dbb4244a0>",
9
+ "_build": "<function SACPolicy._build at 0x7f3dbb424ae0>",
10
+ "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f3dbb424b80>",
11
+ "reset_noise": "<function SACPolicy.reset_noise at 0x7f3dbb424c20>",
12
+ "make_actor": "<function SACPolicy.make_actor at 0x7f3dbb424cc0>",
13
+ "make_critic": "<function SACPolicy.make_critic at 0x7f3dbb424d60>",
14
+ "forward": "<function SACPolicy.forward at 0x7f3dbb424e00>",
15
+ "_predict": "<function SACPolicy._predict at 0x7f3dbb424ea0>",
16
+ "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f3dbb424f40>",
17
  "__abstractmethods__": "frozenset()",
18
+ "_abc_impl": "<_abc._abc_data object at 0x7f3dbb428a80>"
19
  },
20
  "verbose": 0,
21
  "policy_kwargs": {
22
  "use_sde": false
23
  },
24
+ "num_timesteps": 1000000,
25
+ "_total_timesteps": 1000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": 0,
28
  "action_noise": null,
29
+ "start_time": 1730950080089038257,
30
  "learning_rate": 0.0003,
31
+ "tensorboard_log": "runs/mpcmucc8",
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "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"
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
 
39
  },
40
  "_last_original_obs": {
41
  ":type:": "<class 'numpy.ndarray'>",
42
+ ":serialized:": "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"
43
  },
44
+ "_episode_num": 1283,
45
  "use_sde": false,
46
  "sde_sample_freq": -1,
47
  "_current_progress_remaining": 0.0,
48
  "_stats_window_size": 100,
49
  "ep_info_buffer": {
50
  ":type:": "<class 'collections.deque'>",
51
+ ":serialized:": "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"
52
  },
53
  "ep_success_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
56
  },
57
+ "_n_updates": 198000,
58
  "buffer_size": 1000000,
59
  "batch_size": 256,
60
  "learning_starts": 10000,
 
68
  "__module__": "stable_baselines3.common.buffers",
69
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
70
  "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
71
+ "__init__": "<function ReplayBuffer.__init__ at 0x7f3dc626ccc0>",
72
+ "add": "<function ReplayBuffer.add at 0x7f3dc626ce00>",
73
+ "sample": "<function ReplayBuffer.sample at 0x7f3dc626cea0>",
74
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3dc626cf40>",
75
+ "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f3dc626cfe0>)>",
76
  "__abstractmethods__": "frozenset()",
77
+ "_abc_impl": "<_abc._abc_data object at 0x7f3dc62624c0>"
78
  },
79
  "replay_buffer_kwargs": {},
80
  "train_freq": {
ant-v5-sac-simple/ent_coef_optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b9ba4958db3fdb00d9b205e80769d5d091f9de72f7e90ac176e42fa13426488
3
  size 1940
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292520da61c1bcfe37737c37387895138c576058c459c568be7a354c95b9201f
3
  size 1940
ant-v5-sac-simple/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75ccc95d532af1d768c8f8af17e478b55e20fcbf89e8b85c05092f5a859f6d1f
3
  size 1923254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f9aed5adf55016946152a35cccf39f8ac3ded562f749ac7a3e0357dc56bb2f
3
  size 1923254
ant-v5-sac-simple/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12138201bc9696062998400da0985ee8c725686edc0bd371fc429f5cb930cfd5
3
  size 1180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ffe38844eb158460d066114de60cfe39c058a62483dc861443d3284564eb16
3
  size 1180
ant-v5-sac-simple/system_info.txt CHANGED
@@ -1,4 +1,4 @@
1
- - OS: Linux-6.6.56-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Thu Oct 10 19:10:00 UTC 2024
2
  - Python: 3.12.7
3
  - Stable-Baselines3: 2.4.0a10
4
  - PyTorch: 2.4.1+cu121
 
1
+ - OS: Linux-6.6.59-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Fri Nov 1 05:33:52 UTC 2024
2
  - Python: 3.12.7
3
  - Stable-Baselines3: 2.4.0a10
4
  - PyTorch: 2.4.1+cu121
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n Policy class (with both actor and critic) for SAC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ", "__init__": "<function SACPolicy.__init__ at 0x7f142000c400>", "_build": "<function SACPolicy._build at 0x7f142000ca40>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f142000cae0>", "reset_noise": "<function SACPolicy.reset_noise at 0x7f142000cb80>", "make_actor": "<function SACPolicy.make_actor at 0x7f142000cc20>", "make_critic": "<function SACPolicy.make_critic at 0x7f142000ccc0>", "forward": "<function SACPolicy.forward at 0x7f142000cd60>", "_predict": "<function SACPolicy._predict at 0x7f142000ce00>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f142000cea0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f142001c300>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": 0, "action_noise": null, "start_time": 1729211451595343246, "learning_rate": 0.0003, "tensorboard_log": "runs/z50t0ova", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 232, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 18000, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function ReplayBuffer.__init__ at 0x7f142af04c20>", "add": "<function ReplayBuffer.add at 0x7f142af04d60>", "sample": "<function ReplayBuffer.sample at 0x7f142af04e00>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7f142af04ea0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f142af04f40>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1430da9f00>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -8.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "_shape": [105], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "bounded_below": "[ True True True True True True True True]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_above": "[ True True True True True True True True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 5, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.6.56-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Thu Oct 10 19:10:00 UTC 2024", "Python": "3.12.7", "Stable-Baselines3": "2.4.0a10", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n Policy class (with both actor and critic) for SAC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ", "__init__": "<function SACPolicy.__init__ at 0x7f3dbb4244a0>", "_build": "<function SACPolicy._build at 0x7f3dbb424ae0>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f3dbb424b80>", "reset_noise": "<function SACPolicy.reset_noise at 0x7f3dbb424c20>", "make_actor": "<function SACPolicy.make_actor at 0x7f3dbb424cc0>", "make_critic": "<function SACPolicy.make_critic at 0x7f3dbb424d60>", "forward": "<function SACPolicy.forward at 0x7f3dbb424e00>", "_predict": "<function SACPolicy._predict at 0x7f3dbb424ea0>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f3dbb424f40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3dbb428a80>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": 0, "action_noise": null, "start_time": 1730950080089038257, "learning_rate": 0.0003, "tensorboard_log": "runs/mpcmucc8", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 1283, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 198000, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function ReplayBuffer.__init__ at 0x7f3dc626ccc0>", "add": "<function ReplayBuffer.add at 0x7f3dc626ce00>", "sample": "<function ReplayBuffer.sample at 0x7f3dc626cea0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3dc626cf40>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f3dc626cfe0>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3dc62624c0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -8.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "_shape": [105], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "bounded_below": "[ True True True True True True True True]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_above": "[ True True True True True True True True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 5, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.6.59-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Fri Nov 1 05:33:52 UTC 2024", "Python": "3.12.7", "Stable-Baselines3": "2.4.0a10", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae4e669fae3eef35ce9ef03f8ab9f8900f6bf19978f5169c2396d5e971fab060
3
- size 521711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1a5945f43ad07544fc259505545be43356d32d42aa3a99121405ca4cd33cbf
3
+ size 2315134
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 531.5417534, "std_reward": 55.278751973431305, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-18T03:37:16.872049"}
 
1
+ {"mean_reward": 1677.8408050000003, "std_reward": 848.5544021514623, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-07T06:36:46.744692"}