bqzhu commited on
Commit
a0df8fe
1 Parent(s): e6ca28a
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - reinforcement-learning
7
  - stable-baselines3
8
  model-index:
9
- - name: PPO
10
  results:
11
  - task:
12
  type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -667.14 +/- 104.58
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
- # **PPO** Agent playing **LunarLander-v2**
25
- This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
  using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
 
28
  ## Usage (with Stable-baselines3)
 
6
  - reinforcement-learning
7
  - stable-baselines3
8
  model-index:
9
+ - name: ppo
10
  results:
11
  - task:
12
  type: reinforcement-learning
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 303.30 +/- 11.29
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
+ # **ppo** Agent playing **LunarLander-v2**
25
+ This is a trained model of a **ppo** agent playing **LunarLander-v2**
26
  using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
 
28
  ## Usage (with Stable-baselines3)
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 0x7f8bfa4773a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8bfa477430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8bfa4774c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8bfa477550>", "_build": "<function ActorCriticPolicy._build at 0x7f8bfa4775e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8bfa477670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8bfa477700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8bfa477790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8bfa477820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8bfa4778b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8bfa477940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8bfa4779d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8bfa47a140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "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 0x7f8bfa4773a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8bfa477430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8bfa4774c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8bfa477550>", "_build": "<function ActorCriticPolicy._build at 0x7f8bfa4775e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8bfa477670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8bfa477700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8bfa477790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8bfa477820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8bfa4778b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8bfa477940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8bfa4779d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8bfa47a140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 368000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652272866.0520153, "learning_rate": 0.0, "tensorboard_log": "logs", "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": 0.67232, "_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": 19344, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
lunar_ppo.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c1cd64dfe2ee345bac748db37a28988683fa448301162f22de30541ec1dba8a
3
- size 53040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e21bb2fefa8823b90dc78b727e1d2738e8aaf9236b2e8f2d02a5e4335d015a
3
+ size 147609
lunar_ppo/data CHANGED
@@ -21,29 +21,56 @@
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
- "num_timesteps": 0,
25
- "_total_timesteps": 0,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": null,
30
- "learning_rate": 0.0003,
31
- "tensorboard_log": null,
32
  "lr_schedule": {
33
  ":type:": "<class 'function'>",
34
- ":serialized:": "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"
 
 
 
 
 
 
 
 
35
  },
36
- "_last_obs": null,
37
- "_last_episode_starts": null,
38
  "_last_original_obs": null,
39
  "_episode_num": 0,
40
  "use_sde": false,
41
  "sde_sample_freq": -1,
42
- "_current_progress_remaining": 1,
43
  "_stats_window_size": 100,
44
- "ep_info_buffer": null,
45
- "ep_success_buffer": null,
46
- "_n_updates": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  "observation_space": {
48
  ":type:": "<class 'gym.spaces.box.Box'>",
49
  ":serialized:": "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",
@@ -65,20 +92,5 @@
65
  "dtype": "int64",
66
  "_np_random": null
67
  },
68
- "n_envs": 16,
69
- "n_steps": 1024,
70
- "gamma": 0.999,
71
- "gae_lambda": 0.98,
72
- "ent_coef": 0.01,
73
- "vf_coef": 0.5,
74
- "max_grad_norm": 0.5,
75
- "batch_size": 64,
76
- "n_epochs": 4,
77
- "clip_range": {
78
- ":type:": "<class 'function'>",
79
- ":serialized:": "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"
80
- },
81
- "clip_range_vf": null,
82
- "normalize_advantage": true,
83
- "target_kl": null
84
  }
 
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 368000,
25
+ "_total_timesteps": 1000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1652272866.0520153,
30
+ "learning_rate": 0.0,
31
+ "tensorboard_log": "logs",
32
  "lr_schedule": {
33
  ":type:": "<class 'function'>",
34
+ ":serialized:": "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"
35
+ },
36
+ "_last_obs": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "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"
39
+ },
40
+ "_last_episode_starts": {
41
+ ":type:": "<class 'numpy.ndarray'>",
42
+ ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
43
  },
 
 
44
  "_last_original_obs": null,
45
  "_episode_num": 0,
46
  "use_sde": false,
47
  "sde_sample_freq": -1,
48
+ "_current_progress_remaining": 0.67232,
49
  "_stats_window_size": 100,
50
+ "ep_info_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "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"
53
+ },
54
+ "ep_success_buffer": {
55
+ ":type:": "<class 'collections.deque'>",
56
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
57
+ },
58
+ "_n_updates": 19344,
59
+ "n_steps": 2048,
60
+ "gamma": 0.999,
61
+ "gae_lambda": 0.98,
62
+ "ent_coef": 0.01,
63
+ "vf_coef": 0.5,
64
+ "max_grad_norm": 0.5,
65
+ "batch_size": 256,
66
+ "n_epochs": 8,
67
+ "clip_range": {
68
+ ":type:": "<class 'function'>",
69
+ ":serialized:": "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"
70
+ },
71
+ "clip_range_vf": null,
72
+ "normalize_advantage": true,
73
+ "target_kl": null,
74
  "observation_space": {
75
  ":type:": "<class 'gym.spaces.box.Box'>",
76
  ":serialized:": "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",
 
92
  "dtype": "int64",
93
  "_np_random": null
94
  },
95
+ "n_envs": 32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  }
lunar_ppo/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0aa96bf78c4536c6eafd36ce78653aac56f76c12f489666d21b1ace601e8300
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee31ae12df8f8ae4e0d9173c43ae6225ac86f73fc0e5f56c03f49034fb0c3a9
3
+ size 87929
lunar_ppo/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:571b989db29def137d175e88090e3dff8850cdba797536e4b4c1cb1edd929a97
3
  size 43329
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856368906f01bf87532d825189f5f67bec857f90c3892f112143cf0e09e9b529
3
  size 43329
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -667.1442909455393, "std_reward": 104.57665991481022, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T15:12:49.700971"}
 
1
+ {"mean_reward": 303.2985615922571, "std_reward": 11.290599035031635, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-26T15:13:27.778821"}