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 +27 -27
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/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: 234.82 +/- 11.63
|
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 0x7ff76ae17940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff76ae179d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff76ae17a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff76ae17af0>", "_build": "<function ActorCriticPolicy._build at 0x7ff76ae17b80>", "forward": "<function ActorCriticPolicy.forward at 0x7ff76ae17c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff76ae17ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff76ae17d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff76ae17dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff76ae17e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff76ae17ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff76ae17f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff76ae16930>"}, "verbose": 0, "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": 1000006, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677209181814102418, "learning_rate": 0.0030538614898499294, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV0QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMTy9ob21lL3N2bWMvLmxvY2FsL2xpYi9weXRob24zLjgvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjE8vaG9tZS9zdm1jLy5sb2NhbC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9pBGlnNqKAhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAA1/G744leA8xtI6PySKJL/7iJ6+eUBLPwAAgD8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -5.999999999950489e-06, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1428580, "n_steps": 7, "gamma": 0.9736054594654727, "gae_lambda": 0.9068044974477245, "ent_coef": 0.05472803605520063, "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-5.4.0-107-generic-x86_64-with-glibc2.27 # 121~18.04.1-Ubuntu SMP Thu Mar 24 17:21:33 UTC 2022", "Python": "3.8.0", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "False", "Numpy": "1.24.1", "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 0x7f31ac25a790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f31ac25a820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f31ac25a8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f31ac25a940>", "_build": "<function ActorCriticPolicy._build at 0x7f31ac25a9d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f31ac25aa60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f31ac25aaf0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f31ac25ab80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f31ac25ac10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f31ac25aca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f31ac25ad30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f31ac25adc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f31ac25b0c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1677217119280212651, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOARGD5TRDw/O9EXPY61T745aqo9YiqVPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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-5.4.0-107-generic-x86_64-with-glibc2.27 # 121~18.04.1-Ubuntu SMP Thu Mar 24 17:21:33 UTC 2022", "Python": "3.8.0", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "False", "Numpy": "1.24.1", "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:d65223b74111661c71ebce1c8fc55f8b756ef5075adfa39c9a4d7cc0d464b58b
|
3 |
+
size 146303
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,22 +4,22 @@
|
|
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":
|
23 |
"policy_kwargs": {},
|
24 |
"observation_space": {
|
25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
@@ -43,21 +43,21 @@
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 1,
|
46 |
-
"num_timesteps":
|
47 |
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
-
"learning_rate": 0.
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
-
":serialized:": "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
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,24 +67,24 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -
|
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":
|
81 |
-
"gamma": 0.
|
82 |
-
"gae_lambda": 0.
|
83 |
-
"ent_coef": 0.
|
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 0x7f31ac25a790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f31ac25a820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f31ac25a8b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f31ac25a940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f31ac25a9d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f31ac25aa60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f31ac25aaf0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f31ac25ab80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f31ac25ac10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f31ac25aca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f31ac25ad30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f31ac25adc0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f31ac25b0c0>"
|
21 |
},
|
22 |
+
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
"observation_space": {
|
25 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 1,
|
46 |
+
"num_timesteps": 1000448,
|
47 |
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1677217119280212651,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOARGD5TRDw/O9EXPY61T745aqo9YiqVPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.00044800000000000395,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVeRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMICklm9Y6QbkCUhpRSlIwBbJRNUQGMAXSUR0CNnqfjjrAydX2UKGgGaAloD0MINL3EWGYecUCUhpRSlGgVTTEBaBZHQI2gHLxI8Qt1fZQoaAZoCWgPQwi/Y3js57VuQJSGlFKUaBVNOwFoFkdAjaKzbnHNo3V9lChoBmgJaA9DCAD+KVUitG1AlIaUUpRoFU08AWgWR0CNpGrIYFaCdX2UKGgGaAloD0MIuW3fo357b0CUhpRSlGgVTTgBaBZHQI2l/BacI7h1fZQoaAZoCWgPQwhORL+2fvoSQJSGlFKUaBVNSQFoFkdAjaiO3+dbxHV9lChoBmgJaA9DCG1X6INl629AlIaUUpRoFU10AWgWR0CNqmvWYnfEdX2UKGgGaAloD0MIhEcbR6ykb0CUhpRSlGgVTWsBaBZHQI2shxNqQBB1fZQoaAZoCWgPQwiIEi15vDNrQJSGlFKUaBVNXgFoFkdAja948+zMR3V9lChoBmgJaA9DCKkSZW8pFzFAlIaUUpRoFU0XAWgWR0CNsMmDUVi4dX2UKGgGaAloD0MIryXkgx4DcECUhpRSlGgVTTYBaBZHQI2yTZxrBTJ1fZQoaAZoCWgPQwjsGFdcHKUXwJSGlFKUaBVL2mgWR0CNtEw+MZP3dX2UKGgGaAloD0MIU7MHWsFbcUCUhpRSlGgVTbkBaBZHQI22k3hn8Kp1fZQoaAZoCWgPQwio/Gt5ZfVvQJSGlFKUaBVNJQFoFkdAjbgP1UVBU3V9lChoBmgJaA9DCMmSOZZ3TTtAlIaUUpRoFU0pAWgWR0CNupJLdvbXdX2UKGgGaAloD0MIAHFXr+IecUCUhpRSlGgVTZsBaBZHQI28ymhufmN1fZQoaAZoCWgPQwgIPDCA8OJwQJSGlFKUaBVNiwFoFkdAjb7Ac1fmcXV9lChoBmgJaA9DCADK372j3G1AlIaUUpRoFU0/AWgWR0CNwWOQyRCAdX2UKGgGaAloD0MI7kPecnWXZECUhpRSlGgVTcsBaBZHQI3Ec23rleZ1fZQoaAZoCWgPQwjyP/m7d3xtQJSGlFKUaBVNUQFoFkdAjcYzaCcwxnV9lChoBmgJaA9DCCuk/KRae3BAlIaUUpRoFU2YAWgWR0CNyZNh3JPqdX2UKGgGaAloD0MIc0hqoWTfbUCUhpRSlGgVTV8BaBZHQI3Lo2dd3St1fZQoaAZoCWgPQwgUzJiCdYZwQJSGlFKUaBVNQAFoFkdAjc1zgMtsenV9lChoBmgJaA9DCDrLLEKxoXFAlIaUUpRoFU1iAWgWR0CN0EITGo73dX2UKGgGaAloD0MImUuqtlutcECUhpRSlGgVTRkBaBZHQI3Ru6Zpi7V1fZQoaAZoCWgPQwhCI9i4foNrQJSGlFKUaBVNggFoFkdAjdPjW9US7HV9lChoBmgJaA9DCOo8Kv4v23FAlIaUUpRoFU12AWgWR0CN1sVJtix3dX2UKGgGaAloD0MIhPI+jmY/cECUhpRSlGgVTWYBaBZHQI3YnHaN+9d1fZQoaAZoCWgPQwinBprPOb5xQJSGlFKUaBVNPQFoFkdAjdsSIYWLxnV9lChoBmgJaA9DCPSG+8gtYWpAlIaUUpRoFU1XAWgWR0CN3PxEORT1dX2UKGgGaAloD0MISpUoe8uvbUCUhpRSlGgVTT0BaBZHQI3eubwz+FV1fZQoaAZoCWgPQwgUJSGRtqkqQJSGlFKUaBVL72gWR0CN39pXZGrkdX2UKGgGaAloD0MI4lrtYa9ickCUhpRSlGgVTWUBaBZHQI3idF4LThJ1fZQoaAZoCWgPQwjZCpqW2N5vQJSGlFKUaBVNewFoFkdAjeTYWDYh+3V9lChoBmgJaA9DCPim6bODsG5AlIaUUpRoFU1eAWgWR0CN5sxdIGyHdX2UKGgGaAloD0MIYKxvYPJcbUCUhpRSlGgVTVIBaBZHQI3pf7Hhjvx1fZQoaAZoCWgPQwgcQwBw7L5gQJSGlFKUaBVN6ANoFkdAjfHAR02ca3V9lChoBmgJaA9DCLgehevRBW5AlIaUUpRoFU1KAWgWR0CN83ItlI3BdX2UKGgGaAloD0MI4xsKn60SbkCUhpRSlGgVTUkBaBZHQI31TwrlNlB1fZQoaAZoCWgPQwhYdVYLrHBxQJSGlFKUaBVNswFoFkdAjfkt+so2GnV9lChoBmgJaA9DCHmu78PB4GpAlIaUUpRoFU06AWgWR0CN+redkJ8fdX2UKGgGaAloD0MI73GmCVuzb0CUhpRSlGgVTdEBaBZHQI3+vPw/gR91fZQoaAZoCWgPQwiOBYVBmaduQJSGlFKUaBVNfAFoFkdAjgDDZDiOvXV9lChoBmgJaA9DCM3LYfedLm5AlIaUUpRoFU1rAWgWR0COAsgdOqNqdX2UKGgGaAloD0MIibMiaqIVRECUhpRSlGgVTSYBaBZHQI4FPLFGXol1fZQoaAZoCWgPQwi0If/MIBZvQJSGlFKUaBVNYwFoFkdAjgc38fmtAHV9lChoBmgJaA9DCPVjk/yI4zVAlIaUUpRoFU0oAWgWR0COCKLb5/LDdX2UKGgGaAloD0MIhC12+6zza0CUhpRSlGgVTVoBaBZHQI4LcxmCiAV1fZQoaAZoCWgPQwjxDYXP1jFwQJSGlFKUaBVNhwFoFkdAjg2JMxoIwHV9lChoBmgJaA9DCPynGyjwT3BAlIaUUpRoFU1kAWgWR0COD1rWRRuTdX2UKGgGaAloD0MI9wSJ7W6DbECUhpRSlGgVTVEBaBZHQI4SKVObiId1fZQoaAZoCWgPQwgBF2TLcvdrQJSGlFKUaBVNQAFoFkdAjhPjCxeLN3V9lChoBmgJaA9DCEtzK4TVGHFAlIaUUpRoFU1vAWgWR0COFbX1anrIdX2UKGgGaAloD0MIZyyazk4OIsCUhpRSlGgVTQYBaBZHQI4X3R1HOKR1fZQoaAZoCWgPQwhlGk0uhqdwQJSGlFKUaBVNfwFoFkdAjhn+Z5Rj0HV9lChoBmgJaA9DCOAUViroL3FAlIaUUpRoFU2RAWgWR0COHBn1WbPQdX2UKGgGaAloD0MI7GmHv6a6akCUhpRSlGgVTUYBaBZHQI4eyij+Jgt1fZQoaAZoCWgPQwhpAkUsYppDQJSGlFKUaBVNDgFoFkdAjh//ek56t3V9lChoBmgJaA9DCLxcxHdiZHFAlIaUUpRoFU1FAWgWR0COIbIczZYgdX2UKGgGaAloD0MIjJ5b6Io8cECUhpRSlGgVTT8BaBZHQI4khE2HclB1fZQoaAZoCWgPQwilarsJvh5tQJSGlFKUaBVNjQFoFkdAjia3V09yLnV9lChoBmgJaA9DCJZbWg0JcWtAlIaUUpRoFU1DAWgWR0COKGsz2vjfdX2UKGgGaAloD0MIwVPIlXrVbECUhpRSlGgVTVIBaBZHQI4rVxMnJDF1fZQoaAZoCWgPQwiIZTOHpCltQJSGlFKUaBVNLwFoFkdAjizvwmVqvnV9lChoBmgJaA9DCMrfvaPGhB5AlIaUUpRoFUvhaBZHQI4uBnezlcR1fZQoaAZoCWgPQwjgvg6c8w1wQJSGlFKUaBVNMgFoFkdAji9+BYmsvXV9lChoBmgJaA9DCFA6kWCqiW9AlIaUUpRoFU1XAWgWR0COMkDAaef7dX2UKGgGaAloD0MIDVGFP4MvcUCUhpRSlGgVTUsBaBZHQI40EghbGFV1fZQoaAZoCWgPQwglIvyLoFFuQJSGlFKUaBVNVAFoFkdAjjXaVdHDrXV9lChoBmgJaA9DCGwFTUusr25AlIaUUpRoFU0VAWgWR0COOEhJyyUtdX2UKGgGaAloD0MIj6Z6Mv+4G8CUhpRSlGgVS/FoFkdAjjleqR2bG3V9lChoBmgJaA9DCB+F61E4wXBAlIaUUpRoFU1YAWgWR0COOxd43WFwdX2UKGgGaAloD0MIMxr5vGIVcECUhpRSlGgVTWcBaBZHQI4+EkKNQ0p1fZQoaAZoCWgPQwg//WfNzyFwQJSGlFKUaBVNWwFoFkdAjj/mFBY3enV9lChoBmgJaA9DCLrXSX1ZF2tAlIaUUpRoFU0zAWgWR0COQW9zwMH9dX2UKGgGaAloD0MIgjgPJzAbWkCUhpRSlGgVTegDaBZHQI5I9vAGjbl1fZQoaAZoCWgPQwhtA3egToFfQJSGlFKUaBVN6ANoFkdAjlDY5cTrV3V9lChoBmgJaA9DCHPXEvJB5G1AlIaUUpRoFU1JAWgWR0COUpdJrcj8dX2UKGgGaAloD0MIrDdqhemtcECUhpRSlGgVTWkBaBZHQI5Vuu7pV0d1fZQoaAZoCWgPQwg6I0p7A0puQJSGlFKUaBVNYAFoFkdAjlfbGWD6FnV9lChoBmgJaA9DCFN6ppcYDz1AlIaUUpRoFUvvaBZHQI5Y+DQJHAh1fZQoaAZoCWgPQwiz7Elgc6lqQJSGlFKUaBVNTAFoFkdAjlunH3lCC3V9lChoBmgJaA9DCHDqA8m7UnBAlIaUUpRoFU2iAWgWR0COXkb2Dg62dX2UKGgGaAloD0MIKuJ0ki35b0CUhpRSlGgVTWIBaBZHQI5gDqD9Oyp1fZQoaAZoCWgPQwiZmgRvyJxtQJSGlFKUaBVNXQFoFkdAjmLZML4N7XV9lChoBmgJaA9DCBEdAkcCiUpAlIaUUpRoFUvkaBZHQI5j2V1Oj7B1fZQoaAZoCWgPQwhPkNju3nNxQJSGlFKUaBVNQAFoFkdAjmWLy+YdAHV9lChoBmgJaA9DCCgPC7UmJHFAlIaUUpRoFU0xAWgWR0COaBu/k/8mdX2UKGgGaAloD0MI1/m3y/6scUCUhpRSlGgVTXMBaBZHQI5p54Y77sR1fZQoaAZoCWgPQwg8FtukYu1wQJSGlFKUaBVNNQFoFkdAjmtn6MzdlHV9lChoBmgJaA9DCMozL4fdh3BAlIaUUpRoFU1LAWgWR0CObh/NJOFhdX2UKGgGaAloD0MI7L34ov3ecUCUhpRSlGgVTbgBaBZHQI5w00xdpqR1fZQoaAZoCWgPQwgD7+TTY25vQJSGlFKUaBVNTQFoFkdAjnJ/J/5Ly3V9lChoBmgJaA9DCDgQkgVM2CpAlIaUUpRoFUvlaBZHQI50jpu/Dcd1fZQoaAZoCWgPQwhbJsPxfIb2P5SGlFKUaBVL7GgWR0COdaMJhOQAdX2UKGgGaAloD0MIV5i+1xChb0CUhpRSlGgVTTgBaBZHQI53NuxbB451fZQoaAZoCWgPQwihZkgVRTxsQJSGlFKUaBVNOAFoFkdAjnjfbblA/3V9lChoBmgJaA9DCCuKV1nbtG1AlIaUUpRoFU01AWgWR0COe45H3DekdX2UKGgGaAloD0MI7s7abRdQb0CUhpRSlGgVTVcBaBZHQI59ZYgaFVV1fZQoaAZoCWgPQwjkZU0ssCRwQJSGlFKUaBVNHwFoFkdAjn7qJMxoI3VlLg=="
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 3908,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
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 87545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d8347d90ac51ec296e197d011390dc3eb16601449b8e97ab28ad0c94792b7d3
|
3 |
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43265
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbcc7b27a8a8c321471fe0fc80333cc81bfe0a2134aa3d83b44cf7f5c463408e
|
3 |
size 43265
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 234.8201604351588, "std_reward": 11.628730969169302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T13:20:37.641527"}
|