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/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +52 -48
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +8 -6
- 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: 67.84 +/- 119.19
|
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 0x7f51f4820430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51f48204c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f51f4820550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51f48205e0>", "_build": "<function ActorCriticPolicy._build at 0x7f51f4820670>", "forward": "<function ActorCriticPolicy.forward at 0x7f51f4820700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f51f4820790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f51f4820820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f51f48208b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f51f4820940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51f48209d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f51f4820a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f51f4893de0>"}, "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": 16, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678079660735942749, "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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 28, "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 0x78ae9a2aa3b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ae9a2aa440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ae9a2aa4d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ae9a2aa560>", "_build": "<function ActorCriticPolicy._build at 0x78ae9a2aa5f0>", "forward": "<function ActorCriticPolicy.forward at 0x78ae9a2aa680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ae9a2aa710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ae9a2aa7a0>", "_predict": "<function ActorCriticPolicy._predict at 0x78ae9a2aa830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ae9a2aa8c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ae9a2aa950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ae9a2aa9e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78ae9a29a080>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 102400, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693907400144149837, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAABImD7rb28/4HidvKUoQr5RVpi97EsEvgAAAAAAAAAAgMHxPVzLCroKaCA850w0OdJVxrpOyBk6AACAPwAAgD/N3o28SNhJPygAv716lje+Po36vcY3or0AAAAAAAAAAD33m76uauW8CMVAO9aEvDlXzDQ+mEdfugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 300, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJSFlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoI4oQuBqZ77R8Rmtx/Y0K0XgXAowDaW5jlIoRv7hMG/uYxl+3mBZRtVkFyQB1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRKZQRRaXVidWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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 sha256:0644b5cd599576c80cf3faf364867c56057462b73192766c81bc7af06a4ed18d
|
3 |
+
size 146456
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,79 +4,79 @@
|
|
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": {},
|
24 |
-
"
|
25 |
-
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
-
":serialized:": "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",
|
27 |
-
"dtype": "float32",
|
28 |
-
"_shape": [
|
29 |
-
8
|
30 |
-
],
|
31 |
-
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
-
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
-
"bounded_below": "[False False False False False False False False]",
|
34 |
-
"bounded_above": "[False False False False False False False False]",
|
35 |
-
"_np_random": null
|
36 |
-
},
|
37 |
-
"action_space": {
|
38 |
-
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
-
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
-
"n": 4,
|
41 |
-
"_shape": [],
|
42 |
-
"dtype": "int64",
|
43 |
-
"_np_random": null
|
44 |
-
},
|
45 |
-
"n_envs": 16,
|
46 |
-
"num_timesteps": 114688,
|
47 |
"_total_timesteps": 100000,
|
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": {
|
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'>",
|
64 |
-
":serialized:": "
|
65 |
},
|
66 |
"_last_original_obs": null,
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
|
|
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,
|
@@ -87,9 +87,13 @@
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
-
"target_kl": null
|
|
|
|
|
|
|
|
|
95 |
}
|
|
|
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 0x78ae9a2aa3b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ae9a2aa440>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ae9a2aa4d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ae9a2aa560>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x78ae9a2aa5f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x78ae9a2aa680>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x78ae9a2aa710>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ae9a2aa7a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x78ae9a2aa830>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ae9a2aa8c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ae9a2aa950>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x78ae9a2aa9e0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x78ae9a29a080>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 102400,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"_total_timesteps": 100000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1693907400144149837,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
|
|
|
|
|
|
|
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAABImD7rb28/4HidvKUoQr5RVpi97EsEvgAAAAAAAAAAgMHxPVzLCroKaCA850w0OdJVxrpOyBk6AACAPwAAgD/N3o28SNhJPygAv716lje+Po36vcY3or0AAAAAAAAAAD33m76uauW8CMVAO9aEvDlXzDQ+mEdfugAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.02400000000000002,
|
45 |
+
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 300,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "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",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": "Generator(PCG64)"
|
78 |
+
},
|
79 |
+
"n_envs": 4,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
}
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:109f4cbcd078a799a841eb446980689bc97d718a7b646da87690863095f2eb39
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f575e43119cabadf9f520fd1dba9d0603364917794c245560cea9a71d1e4ed42
|
3 |
+
size 43329
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
-
- OS: Linux-5.
|
2 |
-
- Python: 3.
|
3 |
-
- Stable-Baselines3:
|
4 |
-
- PyTorch:
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
-
-
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 67.83778403691682, "std_reward": 119.19126382808612, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-05T10:02:29.895633"}
|