thatgeeman
commited on
Commit
•
6ea878a
1
Parent(s):
b999a84
Unit 1 v1 LunarLander-v2 with PPO #hfRLU1
Browse files- README.md +1 -1
- config.json +1 -1
- ppo_model.zip +2 -2
- ppo_model/data +18 -18
- ppo_model/policy.optimizer.pth +1 -1
- ppo_model/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 278.97 +/- 18.80
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f089bdb64c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f089bdb6550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f089bdb65e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f089bdb6670>", "_build": "<function ActorCriticPolicy._build at 0x7f089bdb6700>", "forward": "<function ActorCriticPolicy.forward at 0x7f089bdb6790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f089bdb6820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f089bdb68b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f089bdb6940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f089bdb69d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f089bdb6a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f089bdb6af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f089be2bab0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678138197063909153, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALWejr69XX48JBtDu8g4hTnuHAe+biNrOgAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fbe1dc07ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbe1dc07d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbe1dc07dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbe1dc07e50>", "_build": "<function ActorCriticPolicy._build at 0x7fbe1dc07ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7fbe1dc07f70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbe1dc0b040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbe1dc0b0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbe1dc0b160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbe1dc0b1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbe1dc0b280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbe1dc0b310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbe1dc038a0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678283955986951092, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAC38GL64QPQ6B0mbtN7iMzK90zu8ZtQBNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 9770, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo_model.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d100fa4c2527b8d2caa2542ac7dafe9c8dc54d6269285a5fb34f9a9d5e10e1d
|
3 |
+
size 146679
|
ppo_model/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -48,7 +48,7 @@
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -70,13 +70,13 @@
|
|
70 |
"_current_progress_remaining": -0.00044800000000000395,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
@@ -84,7 +84,7 @@
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fbe1dc07ca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbe1dc07d30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbe1dc07dc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbe1dc07e50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fbe1dc07ee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fbe1dc07f70>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbe1dc0b040>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbe1dc0b0d0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fbe1dc0b160>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbe1dc0b1f0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbe1dc0b280>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbe1dc0b310>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fbe1dc038a0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1678283955986951092,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAC38GL64QPQ6B0mbtN7iMzK90zu8ZtQBNAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
70 |
"_current_progress_remaining": -0.00044800000000000395,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 9770,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
ppo_model/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:105288a1dfbad1f0c114ac16fe1a0f40ca33bdb5952671139741b0f3f28e7e52
|
3 |
size 87929
|
ppo_model/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a981673b4be6af12f55513a5bc85d504cf45dba2257df52e2d6ad10911f6da2e
|
3 |
size 43393
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 278.9707014491968, "std_reward": 18.796165422428555, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T14:56:10.731284"}
|