Commit
·
df8f80f
1
Parent(s):
72c6d4c
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +23 -23
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +3 -3
- 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: 262.02 +/- 72.81
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7fe215d86c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe215d86cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe215d86d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe215d86dd0>", "_build": "<function ActorCriticPolicy._build at 0x7fe215d86e60>", "forward": "<function ActorCriticPolicy.forward at 0x7fe215d86ef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe215d86f80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe215d8e050>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe215d8e0e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe215d8e170>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe215d8e200>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fe215dd4ae0>"}, "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": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1668915666137927945, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 372, "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-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f1b2eb0fdc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1b2eb0fe50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1b2eb0fee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1b2eb0ff70>", "_build": "<function ActorCriticPolicy._build at 0x7f1b2eb16040>", "forward": "<function ActorCriticPolicy.forward at 0x7f1b2eb160d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1b2eb16160>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1b2eb161f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1b2eb16280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1b2eb16310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1b2eb163a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f1b2eb0d480>"}, "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": 32, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670753127817086923, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.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:fd5ed264b16c677e4e45f214929b7f70ec19e4f632a03a730e858a50cf2b521d
|
3 |
+
size 147794
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -41,41 +41,41 @@
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
-
"n_envs":
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -86,7 +86,7 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f1b2eb0fdc0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1b2eb0fe50>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1b2eb0fee0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1b2eb0ff70>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1b2eb16040>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1b2eb160d0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1b2eb16160>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1b2eb161f0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1b2eb16280>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1b2eb16310>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1b2eb163a0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f1b2eb0d480>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 32,
|
45 |
+
"num_timesteps": 3014656,
|
46 |
+
"_total_timesteps": 3000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670753127817086923,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.004885333333333408,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 368,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
ppo-LunarLander-v2/policy.optimizer.pth
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 sha256:453bfe55f33dfb477ba91433b13b404da44601007e4217a535f7513048d9b5eb
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df8fb4a3fdab18d8fc52b7324a4bac9bc17e05eda859d5c4063be56828088c70
|
3 |
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.10.133+-x86_64-with-
|
2 |
-
Python: 3.
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
-
PyTorch: 1.
|
5 |
GPU Enabled: True
|
6 |
Numpy: 1.21.6
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
GPU Enabled: True
|
6 |
Numpy: 1.21.6
|
7 |
Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 262.0159966818103, "std_reward": 72.80697304898445, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-11T10:50:34.697594"}
|