Upload model to Hugging Face
Browse files- PPO-punish-stag-at-end.zip +1 -1
- PPO-punish-stag-at-end/data +16 -16
- PPO-punish-stag-at-end/policy.optimizer.pth +1 -1
- PPO-punish-stag-at-end/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
PPO-punish-stag-at-end.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 150420
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ca449879b22e88506fa7b19612e3b110897d96dd51037e76a73851c8420f84
|
3 |
size 150420
|
PPO-punish-stag-at-end/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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": true,
|
23 |
"policy_kwargs": {},
|
@@ -48,7 +48,7 @@
|
|
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": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -70,7 +70,7 @@
|
|
70 |
"_current_progress_remaining": -0.0035199999999999676,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
|
|
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 0x7fcc6b6f11b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc6b6f1240>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc6b6f12d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc6b6f1360>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fcc6b6f13f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fcc6b6f1480>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcc6b6f1510>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc6b6f15a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fcc6b6f1630>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc6b6f16c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc6b6f1750>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc6b6f17e0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fcc6b6dddc0>"
|
21 |
},
|
22 |
"verbose": true,
|
23 |
"policy_kwargs": {},
|
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1681935308922766727,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADUiyULf5eO/AADIQprsJEKa7CRCFmhXQn1Pc0IAAMhCAADIQnL7fEKn0IZDW5Q4QAAAyEKa7CRCmuwkQhZoV0J9T3NCAADIQgAAyEJy+3xCLTuVQ4XJAcAAAMhCmuwkQqziMkIWaFdCAADIQgAAyEIRZLhCcvt8Qkb65UJXJds/AADIQprsJEKa7CRCFmhXQn1Pc0IAAMhCAADIQnL7fEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
70 |
"_current_progress_remaining": -0.0035199999999999676,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
PPO-punish-stag-at-end/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44d9693b815c08f0f7556622ccdb738cd0c54c76259502b2b926671037ad2513
|
3 |
size 90105
|
PPO-punish-stag-at-end/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 44417
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c95302cb5f54c8490d084ddf09c13370a6ec0b54c795a26f0a58e5407667943c
|
3 |
size 44417
|
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: RoombaAToB-punish-stag-at-end
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: RoombaAToB-punish-stag-at-end
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -2014.75 +/- 15.01
|
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 0x7f02df7f11b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f02df7f1240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f02df7f12d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f02df7f1360>", "_build": "<function ActorCriticPolicy._build at 0x7f02df7f13f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f02df7f1480>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f02df7f1510>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f02df7f15a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f02df7f1630>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f02df7f16c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f02df7f1750>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f02df7f17e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f02dfa9c700>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [10], "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]", "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]", "bounded_below": "[ True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 401408, "_total_timesteps": 400000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681933085765993176, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV4QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAGzBqkPlDgTAAADIQprsJEKa7CRCFmhXQn1Pc0IAAMhCAADIQnL7fEIAgVRDjaX4vwAAyEKa7CRCmuwkQhZoV0J9T3NCAADIQgAAyEJy+3xC3UxdQwF/zL8AAMhCmuwkQprsJEIWaFdCfU9zQgAAyEIAAMhCcvt8QjqpykEmo0G/AADIQs9HQkJhtzhCjGxAQrvzTUIAAMhCAADIQpZ/kkKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"}, "_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": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1360, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.5, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV4QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVy9ob21lL25vaXNlYnJpZGdlLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7fcc6b6f11b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcc6b6f1240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcc6b6f12d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcc6b6f1360>", "_build": "<function ActorCriticPolicy._build at 0x7fcc6b6f13f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fcc6b6f1480>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcc6b6f1510>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcc6b6f15a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcc6b6f1630>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcc6b6f16c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcc6b6f1750>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcc6b6f17e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcc6b6dddc0>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [10], "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]", "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]", "bounded_below": "[ True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 401408, "_total_timesteps": 400000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681935308922766727, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAADUiyULf5eO/AADIQprsJEKa7CRCFmhXQn1Pc0IAAMhCAADIQnL7fEKn0IZDW5Q4QAAAyEKa7CRCmuwkQhZoV0J9T3NCAADIQgAAyEJy+3xCLTuVQ4XJAcAAAMhCmuwkQqziMkIWaFdCAADIQgAAyEIRZLhCcvt8Qkb65UJXJds/AADIQprsJEKa7CRCFmhXQn1Pc0IAAMhCAADIQnL7fEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"}, "_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": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIrkfhehRYj8CUhpRSlIwBbJRNLQGMAXSUR0CZ39bKA8SxdX2UKGgGaAloD0MI+tAF9Y1bj8CUhpRSlGgVTS0BaBZHQJnf/FuNxVB1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAmeHZ++dsi3V9lChoBmgJaA9DCKt3uB3qJ5DAlIaUUpRoFU0tAWgWR0CZ6IvQF9rodX2UKGgGaAloD0MISOF6FK7Rj8CUhpRSlGgVTS0BaBZHQJnsCiTMaCN1fZQoaAZoCWgPQwhRvMrapimQwJSGlFKUaBVNLQFoFkdAmew1nmJWNnV9lChoBmgJaA9DCK5H4XoUWI/AlIaUUpRoFU0tAWgWR0CZ7qKcurZKdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJn270+TvAp1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAmfpZiRW913V9lChoBmgJaA9DCFAaahRCN5DAlIaUUpRoFU0tAWgWR0CZ+pO+7Dl6dX2UKGgGaAloD0MImpmZmZlXj8CUhpRSlGgVTS0BaBZHQJn8lbC79Q51fZQoaAZoCWgPQwjkTulgLSaQwJSGlFKUaBVNLQFoFkdAmgTuk+HJtHV9lChoBmgJaA9DCORO6WAtJpDAlIaUUpRoFU0tAWgWR0CaCKdOqNp/dX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJoIy4UeuFJ1fZQoaAZoCWgPQwhRvMrapimQwJSGlFKUaBVNLQFoFkdAmgtxAGB4EHV9lChoBmgJaA9DCPrQBfWNW4/AlIaUUpRoFU0tAWgWR0CaFCcDbJwLdX2UKGgGaAloD0MILZeNzpkwkMCUhpRSlGgVTS0BaBZHQJoXq9vjwQV1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAmhfKU3XI2nV9lChoBmgJaA9DCIoipG4HX4/AlIaUUpRoFU0tAWgWR0CaGbwZwXImdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJpB3xaxHG11fZQoaAZoCWgPQwjkTulgLSaQwJSGlFKUaBVNLQFoFkdAmkX4Rh+fAnV9lChoBmgJaA9DCK5H4XoUWI/AlIaUUpRoFU0tAWgWR0CaRiXZoPCmdX2UKGgGaAloD0MIPQrXo3AkkMCUhpRSlGgVTS0BaBZHQJpI2LXL/0d1fZQoaAZoCWgPQwh4exACwr6QwJSGlFKUaBVNLQFoFkdAmlKWbCrLhnV9lChoBmgJaA9DCFk2c0iqfo/AlIaUUpRoFU0tAWgWR0CaVeDIzWPMdX2UKGgGaAloD0MIQrKACTxbj8CUhpRSlGgVTS0BaBZHQJpWFm7J4jd1fZQoaAZoCWgPQwhiLT4FgB+QwJSGlFKUaBVNLQFoFkdAmlfdMsYl6nV9lChoBmgJaA9DCKt3uB3qJ5DAlIaUUpRoFU0tAWgWR0CaXx3yZrpJdX2UKGgGaAloD0MIPQrXo3AkkMCUhpRSlGgVTS0BaBZHQJpiFkmQbMp1fZQoaAZoCWgPQwiKIqRuB1+PwJSGlFKUaBVNLQFoFkdAmmJTQqqfe3V9lChoBmgJaA9DCPYoXI/CV4/AlIaUUpRoFU0tAWgWR0CaZN7IkqtpdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJpuf1zySV51fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAmnHfl6qsEXV9lChoBmgJaA9DCFdgyOq2K4/AlIaUUpRoFU0tAWgWR0CachzTF2mpdX2UKGgGaAloD0MIiiKkbgdfj8CUhpRSlGgVTS0BaBZHQJp0hloUSIx1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAmn2+5SWJJ3V9lChoBmgJaA9DCKt3uB3qJ5DAlIaUUpRoFU0tAWgWR0CagagHu7YkdX2UKGgGaAloD0MIvymsVCAtkMCUhpRSlGgVTS0BaBZHQJqB0aisXBR1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAmoRPHHWBjHV9lChoBmgJaA9DCFdgyOq2K4/AlIaUUpRoFU0tAWgWR0CajPgEEC/5dX2UKGgGaAloD0MI9ihcj8JXj8CUhpRSlGgVTS0BaBZHQJqPSGqPwNN1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAmo9i9AX2unV9lChoBmgJaA9DCPrQBfWNW4/AlIaUUpRoFU0tAWgWR0CakWGIbfgrdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJqZQzzmOlx1fZQoaAZoCWgPQwjkTulgLSaQwJSGlFKUaBVNLQFoFkdAmp1Rf0Eov3V9lChoBmgJaA9DCORO6WAtJpDAlIaUUpRoFU0tAWgWR0CanYIyCWeIdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJqgYGD+R5l1fZQoaAZoCWgPQwgK16NwPSiPwJSGlFKUaBVNLQFoFkdAmtD5/CqIanV9lChoBmgJaA9DCPrQBfWNW4/AlIaUUpRoFU0tAWgWR0Ca1KxZMcp9dX2UKGgGaAloD0MIGeWZl2MrkMCUhpRSlGgVTS0BaBZHQJrU8csDnvF1fZQoaAZoCWgPQwjpuBrZxcSQwJSGlFKUaBVNLQFoFkdAmtcyUHIIW3V9lChoBmgJaA9DCD0K16NwJJDAlIaUUpRoFU0tAWgWR0Ca37gdfb9IdX2UKGgGaAloD0MIQdgpVu3oj8CUhpRSlGgVTS0BaBZHQJrjYfZElVt1fZQoaAZoCWgPQwiKIqRuB1+PwJSGlFKUaBVNLQFoFkdAmuOQdXDFZXV9lChoBmgJaA9DCKt3uB3qJ5DAlIaUUpRoFU0tAWgWR0Ca5WQfIS13dX2UKGgGaAloD0MIPQrXo3AkkMCUhpRSlGgVTS0BaBZHQJruBCOWBz51fZQoaAZoCWgPQwgK16NwPUCPwJSGlFKUaBVNLQFoFkdAmvGA9q1w53V9lChoBmgJaA9DCPj+Bu21Q5DAlIaUUpRoFU0tAWgWR0Ca8azabnX/dX2UKGgGaAloD0MI5E7pYC0mkMCUhpRSlGgVTS0BaBZHQJr0V9ZzPrx1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAmv2B7NSqEXV9lChoBmgJaA9DCK5H4XoUWI/AlIaUUpRoFU0tAWgWR0CbATIcinpCdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJsBdmSQo1F1fZQoaAZoCWgPQwjRAx+DtV6PwJSGlFKUaBVNLQFoFkdAmwQkA1ejVXV9lChoBmgJaA9DCKt3uB3qJ5DAlIaUUpRoFU0tAWgWR0CbDNYHgP3BdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJsRf/Khcqx1fZQoaAZoCWgPQwiKIqRuB1+PwJSGlFKUaBVNLQFoFkdAmxGr0Bfa6HV9lChoBmgJaA9DCK5H4XoUWI/AlIaUUpRoFU0tAWgWR0CbFM2mHgxbdX2UKGgGaAloD0MIhe/9DdookMCUhpRSlGgVTS0BaBZHQJsfwZFXq7l1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAmyQimMwUQHV9lChoBmgJaA9DCPrQBfWNW4/AlIaUUpRoFU0tAWgWR0CbJFOmBOHndX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJsmTT3IuGt1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAmy7vJiiItXV9lChoBmgJaA9DCORO6WAtJpDAlIaUUpRoFU0tAWgWR0CbMwMh5gPVdX2UKGgGaAloD0MII7w9CKFgj8CUhpRSlGgVTS0BaBZHQJszM3vQWvd1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAm18DV+Zw43V9lChoBmgJaA9DCMed0sFa1I/AlIaUUpRoFU0tAWgWR0CbaSWznieedX2UKGgGaAloD0MInkFD/2Rbj8CUhpRSlGgVTS0BaBZHQJttZFrl/6R1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAm22rbHp8nnV9lChoBmgJaA9DCBSuR+F6zo/AlIaUUpRoFU0tAWgWR0CbcLR4yGi6dX2UKGgGaAloD0MICtejcD0jkMCUhpRSlGgVTS0BaBZHQJt5wOuq3mV1fZQoaAZoCWgPQwj60AX1jVuPwJSGlFKUaBVNLQFoFkdAm3zhppN9IHV9lChoBmgJaA9DCPrQBfWNW4/AlIaUUpRoFU0tAWgWR0CbfPrD63y7dX2UKGgGaAloD0MI0QMfg7Vej8CUhpRSlGgVTS0BaBZHQJt+kIAwPAh1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAm4ZBk/bCanV9lChoBmgJaA9DCD0K16NwJJDAlIaUUpRoFU0tAWgWR0CbigAk9lmOdX2UKGgGaAloD0MIrkfhehRYj8CUhpRSlGgVTS0BaBZHQJuKLbM5fdB1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAm4zYVRDTjXV9lChoBmgJaA9DCMed0sFaXI/AlIaUUpRoFU0tAWgWR0Cblshr30wrdX2UKGgGaAloD0MIrkfhehQoj8CUhpRSlGgVTS0BaBZHQJuatVYISlF1fZQoaAZoCWgPQwg9CtejcCSQwJSGlFKUaBVNLQFoFkdAm5rguM+/xnV9lChoBmgJaA9DCD0K16NwJJDAlIaUUpRoFU0tAWgWR0CbnZUzKs+3dX2UKGgGaAloD0MI5E7pYC0mkMCUhpRSlGgVTS0BaBZHQJum8IyCWeJ1fZQoaAZoCWgPQwhmZmZmZiiPwJSGlFKUaBVNLQFoFkdAm6qkRvm5lXV9lChoBmgJaA9DCK5H4XoUWI/AlIaUUpRoFU0tAWgWR0CbqsYcvM8pdX2UKGgGaAloD0MIPQrXo3AkkMCUhpRSlGgVTS0BaBZHQJus8hJRO1x1fZQoaAZoCWgPQwiuR+F6FFiPwJSGlFKUaBVNLQFoFkdAm7Ui5mRNh3V9lChoBmgJaA9DCD0K16NwJJDAlIaUUpRoFU0tAWgWR0Cbt8IwdsBRdX2UKGgGaAloD0MIPQrXo3AkkMCUhpRSlGgVTS0BaBZHQJu33C/Glyl1fZQoaAZoCWgPQwg9CtejcD+PwJSGlFKUaBVNLQFoFkdAm7lEXpGFz3V9lChoBmgJaA9DCD0K16NwJJDAlIaUUpRoFU0tAWgWR0Cbv07sOXmedWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1360, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.5, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -2014.7519999999997, "std_reward": 15.013909417603244, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T13:45:11.228421"}
|