deutschmann
commited on
Commit
•
5ef6c5c
1
Parent(s):
007b0e4
Longer training
Browse files- PPO-MLP.zip +2 -2
- PPO-MLP/data +27 -27
- PPO-MLP/policy.optimizer.pth +2 -2
- PPO-MLP/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
PPO-MLP.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:b5aa7089979dc0ecf086cf4f40ae2e7b04b33a372b263c95cfcfbf1191bf1bda
|
3 |
+
size 143274
|
PPO-MLP/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc._abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -41,49 +41,49 @@
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
-
"n_envs":
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
-
"tensorboard_log":
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
":serialized:": "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"
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
-
"n_steps":
|
80 |
-
"gamma": 0.
|
81 |
-
"gae_lambda": 0.
|
82 |
-
"ent_coef": 0.
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "gAWVIwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjHkvVXNlcnMvcGF0cmljay8ucHllbnYvdmVyc2lvbnMvMy45LjExL2VudnMvaGYtZGVlcC1ybC1jbGFzcy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIx5L1VzZXJzL3BhdHJpY2svLnB5ZW52L3ZlcnNpb25zLzMuOS4xMS9lbnZzL2hmLWRlZXAtcmwtY2xhc3MvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x177986550>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1779865e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x177986670>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x177986700>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x177986790>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x177986820>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1779868b0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x177986940>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1779869d0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x177986a60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x177986af0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x17798a780>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 1,
|
45 |
+
"num_timesteps": 1001472,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1651819683.2607381,
|
51 |
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": "runs/2cn87197",
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
":serialized:": "gAWVIwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjHkvVXNlcnMvcGF0cmljay8ucHllbnYvdmVyc2lvbnMvMy45LjExL2VudnMvaGYtZGVlcC1ybC1jbGFzcy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIx5L1VzZXJzL3BhdHJpY2svLnB5ZW52L3ZlcnNpb25zLzMuOS4xMS9lbnZzL2hmLWRlZXAtcmwtY2xhc3MvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGggfZR9lChoF2gOjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGIwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALOQfD2n7VY+qNv9vdoYr74Sg409m02QvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0014719999999999178,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 4890,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
+
"n_epochs": 10,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
PPO-MLP/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:fecfbed98f610e6f372b4e64858021744b2f69f007f7593947275fe6000e468b
|
3 |
+
size 84637
|
PPO-MLP/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43073
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:573a2fae267bccb6dff3358163d22c858e972b44e59a9e0026df60128e01288d
|
3 |
size 43073
|
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 247.30 +/- 74.79
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x17a054040>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17a0540d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17a054160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17a0541f0>", "_build": "<function ActorCriticPolicy._build at 0x17a054280>", "forward": "<function ActorCriticPolicy.forward at 0x17a054310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17a0543a0>", "_predict": "<function ActorCriticPolicy._predict at 0x17a054430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17a0544c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17a054550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17a0545e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17976c480>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651742929.270856, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.9.11", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.22.3", "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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x177986550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1779865e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x177986670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x177986700>", "_build": "<function ActorCriticPolicy._build at 0x177986790>", "forward": "<function ActorCriticPolicy.forward at 0x177986820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1779868b0>", "_predict": "<function ActorCriticPolicy._predict at 0x177986940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1779869d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x177986a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x177986af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17798a780>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651819683.2607381, "learning_rate": 0.0003, "tensorboard_log": "runs/2cn87197", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALOQfD2n7VY+qNv9vdoYr74Sg409m02QvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0014719999999999178, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4890, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "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": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:46:32 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T6000", "Python": "3.9.11", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
replay.mp4
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:bccf85e8da44263aab14ffbda8ae5a8aa44fe02a345aa540f4ef0f0d76411cc3
|
3 |
+
size 386472
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 247.30166467451772, "std_reward": 74.78732097032889, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T09:27:00.807013"}
|