Commit
•
0f5c71c
1
Parent(s):
24fc3a0
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 +25 -25
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/pytorch_variables.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +6 -7
- 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: 279.07 +/- 18.61
|
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 0x7c9fc6415b40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9fc6415bd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9fc6415c60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9fc6415cf0>", "_build": "<function ActorCriticPolicy._build at 0x7c9fc6415d80>", "forward": "<function ActorCriticPolicy.forward at 0x7c9fc6415e10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9fc6415ea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9fc6415f30>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9fc6415fc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9fc6416050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9fc64160e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9fc6416170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9fc65a7b80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721125920203929089, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZmJTz5MNo+XlK0vYllor6Igay9sn/NPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "_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": 3908, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x1147ade50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1147adee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1147adf70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1147b1040>", "_build": "<function ActorCriticPolicy._build at 0x1147b10d0>", "forward": "<function ActorCriticPolicy.forward at 0x1147b1160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x1147b11f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1147b1280>", "_predict": "<function ActorCriticPolicy._predict at 0x1147b1310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1147b13a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1147b1430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1147b14c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1147b2440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2500608, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1721132653255899000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABNu5K93Mg5PtJ6uT1plpe+z1xRPBl/Ij0AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00024320000000011, "_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": 9768, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": "macOS-14.4-arm64-arm-64bit Darwin Kernel Version 23.4.0: Wed Feb 21 21:45:49 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6020", "Python": "3.9.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1", "GPU Enabled": "False", "Numpy": "2.0.0", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
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 sha256:45a9498b2d509dfc2b3ed14dd4a0c90d44140ddb2c1772e1b4b8571541bb4882
|
3 |
+
size 147117
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,57 +4,57 @@
|
|
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._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
-
":serialized:": "
|
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]",
|
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
@@ -87,13 +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 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "
|
98 |
}
|
99 |
}
|
|
|
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 0x1147ade50>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1147adee0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1147adf70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1147b1040>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x1147b10d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x1147b1160>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x1147b11f0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1147b1280>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x1147b1310>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1147b13a0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1147b1430>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x1147b14c0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x1147b2440>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2500608,
|
25 |
+
"_total_timesteps": 2500000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1721132653255899000,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABNu5K93Mg5PtJ6uT1plpe+z1xRPBl/Ij0AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.00024320000000011,
|
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": 9768,
|
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]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:412866872047c8d374ecee62df5e2a656db6441d17fd226dbfa71d9402b737c1
|
3 |
+
size 87978
|
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 sha256:19132c59b077cb20f3cdeac7eb053ca164b3c1b7495534dcbdbbbd1f769f4089
|
3 |
+
size 43634
|
ppo-LunarLander-v2/pytorch_variables.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
|
3 |
size 864
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
-
- OS:
|
2 |
-
- Python: 3.
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.3.
|
5 |
-
- GPU Enabled:
|
6 |
-
- Numpy:
|
7 |
-
- Cloudpickle:
|
8 |
- Gymnasium: 0.28.1
|
9 |
-
- OpenAI Gym: 0.25.2
|
|
|
1 |
+
- OS: macOS-14.4-arm64-arm-64bit Darwin Kernel Version 23.4.0: Wed Feb 21 21:45:49 PST 2024; root:xnu-10063.101.15~2/RELEASE_ARM64_T6020
|
2 |
+
- Python: 3.9.6
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.3.1
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 2.0.0
|
7 |
+
- Cloudpickle: 3.0.0
|
8 |
- Gymnasium: 0.28.1
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 279.07376250000004, "std_reward": 18.612652626409538, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T14:36:12.754346"}
|