Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- my_model.zip +2 -2
- my_model/data +26 -38
- my_model/policy.optimizer.pth +2 -2
- my_model/policy.pth +2 -2
- my_model/system_info.txt +6 -5
- 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: -238.41 +/- 52.85
|
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 0x17ffc32e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17ffc3380>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17ffc3420>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17ffc34c0>", "_build": "<function ActorCriticPolicy._build at 0x17ffc3560>", "forward": "<function ActorCriticPolicy.forward at 0x17ffc3600>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x17ffc36a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17ffc3740>", "_predict": "<function ActorCriticPolicy._predict at 0x17ffc37e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17ffc3880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17ffc3920>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17ffc39c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17ffbbcc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 24416, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695803713286863000, "learning_rate": 0.0003, "tensorboard_log": null, "_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": 0.983616, "_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": 4, "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": 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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-13.5-arm64-arm-64bit Darwin Kernel Version 22.6.0: Wed Jul 5 22:22:05 PDT 2023; root:xnu-8796.141.3~6/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1", "GPU Enabled": "False", "Numpy": "1.26.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
|
|
|
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 0x7c4a35d76f80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c4a35d77010>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c4a35d770a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c4a35d77130>", "_build": "<function ActorCriticPolicy._build at 0x7c4a35d771c0>", "forward": "<function ActorCriticPolicy.forward at 0x7c4a35d77250>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c4a35d772e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c4a35d77370>", "_predict": "<function ActorCriticPolicy._predict at 0x7c4a35d77400>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c4a35d77490>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c4a35d77520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c4a35d775b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c4a35f20340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 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"}}
|
my_model.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 sha256:429a622a4239f211597aa1f7db750be042b1ff4e800b4347246ba4a0460332e3
|
3 |
+
size 53849
|
my_model/data
CHANGED
@@ -4,57 +4,45 @@
|
|
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 |
-
|
34 |
-
":serialized:": "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"
|
35 |
-
},
|
36 |
-
"_last_episode_starts": {
|
37 |
-
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
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 |
-
|
48 |
-
|
49 |
-
},
|
50 |
-
"ep_success_buffer": {
|
51 |
-
":type:": "<class 'collections.deque'>",
|
52 |
-
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
-
},
|
54 |
-
"_n_updates": 4,
|
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 +57,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
@@ -87,13 +75,13 @@
|
|
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 0x7c4a35d76f80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c4a35d77010>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c4a35d770a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c4a35d77130>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7c4a35d771c0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7c4a35d77250>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7c4a35d772e0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c4a35d77370>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7c4a35d77400>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c4a35d77490>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c4a35d77520>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7c4a35d775b0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c4a35f20340>"
|
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": 0.0,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
+
"_last_obs": null,
|
33 |
+
"_last_episode_starts": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"_last_original_obs": null,
|
35 |
"_episode_num": 0,
|
36 |
"use_sde": false,
|
37 |
"sde_sample_freq": -1,
|
38 |
+
"_current_progress_remaining": 1.0,
|
39 |
"_stats_window_size": 100,
|
40 |
+
"ep_info_buffer": null,
|
41 |
+
"ep_success_buffer": null,
|
42 |
+
"_n_updates": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
"observation_space": {
|
44 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
45 |
+
":serialized:": "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",
|
46 |
"dtype": "float32",
|
47 |
"bounded_below": "[ True True True True True True True True]",
|
48 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
57 |
},
|
58 |
"action_space": {
|
59 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
60 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
61 |
"n": "4",
|
62 |
"start": "0",
|
63 |
"_shape": [],
|
|
|
75 |
"n_epochs": 4,
|
76 |
"clip_range": {
|
77 |
":type:": "<class 'function'>",
|
78 |
+
":serialized:": "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"
|
79 |
},
|
80 |
"clip_range_vf": null,
|
81 |
"normalize_advantage": true,
|
82 |
"target_kl": null,
|
83 |
"lr_schedule": {
|
84 |
":type:": "<class 'function'>",
|
85 |
+
":serialized:": "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"
|
86 |
}
|
87 |
}
|
my_model/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:e0aa96bf78c4536c6eafd36ce78653aac56f76c12f489666d21b1ace601e8300
|
3 |
+
size 687
|
my_model/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 sha256:4514c1af8a07dd0c81efb20e38c8914e09d5644258c5a3dfad70484e7e6cada5
|
3 |
+
size 43329
|
my_model/system_info.txt
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
-
- OS:
|
2 |
-
- Python: 3.
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.0.1
|
5 |
-
- GPU Enabled:
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
|
|
|
1 |
+
- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 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
ADDED
Binary file (165 kB). View file
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -238.41041788265574, "std_reward": 52.84916675394408, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-27T08:36:41.172927"}
|