Baseline: LR=3e-4/.99, epochs=2e6
Browse files- LunarLander-v2-PPO.zip +2 -2
- LunarLander-v2-PPO/data +30 -23
- LunarLander-v2-PPO/policy.optimizer.pth +2 -2
- LunarLander-v2-PPO/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
LunarLander-v2-PPO.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 sha256:3e3f10826b8d78f6534fa5096f79d134267ba74d78e790cf3d330219035f48bf
|
3 |
+
size 145816
|
LunarLander-v2-PPO/data
CHANGED
@@ -4,21 +4,21 @@
|
|
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_data object at
|
20 |
},
|
21 |
-
"verbose":
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
@@ -42,21 +42,28 @@
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
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":
|
|
|
|
|
|
|
|
|
|
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
-
":type:": "<class '
|
55 |
-
":serialized:": "
|
|
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -66,16 +73,16 @@
|
|
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": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
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 0x7f444c21f0e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f444c21f170>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f444c21f200>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f444c21f290>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f444c21f320>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f444c21f3b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f444c21f440>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f444c21f4d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f444c21f560>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f444c21f5f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f444c21f680>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f444c26b840>"
|
20 |
},
|
21 |
+
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 2015232,
|
46 |
+
"_total_timesteps": 2000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652550516.0483027,
|
51 |
+
"learning_rate": {
|
52 |
+
":type:": "<class '__main__.Scheduler'>",
|
53 |
+
":serialized:": "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",
|
54 |
+
"learning_rate": 2.506191890196153e-05,
|
55 |
+
"decay": 0.99
|
56 |
+
},
|
57 |
"tensorboard_log": null,
|
58 |
"lr_schedule": {
|
59 |
+
":type:": "<class '__main__.Scheduler'>",
|
60 |
+
":serialized:": "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",
|
61 |
+
"learning_rate": 2.506191890196153e-05,
|
62 |
+
"decay": 0.99
|
63 |
},
|
64 |
"_last_obs": {
|
65 |
":type:": "<class 'numpy.ndarray'>",
|
66 |
+
":serialized:": "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"
|
67 |
},
|
68 |
"_last_episode_starts": {
|
69 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
73 |
"_episode_num": 0,
|
74 |
"use_sde": false,
|
75 |
"sde_sample_freq": -1,
|
76 |
+
"_current_progress_remaining": -0.007616000000000067,
|
77 |
"ep_info_buffer": {
|
78 |
":type:": "<class 'collections.deque'>",
|
79 |
+
":serialized:": "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"
|
80 |
},
|
81 |
"ep_success_buffer": {
|
82 |
":type:": "<class 'collections.deque'>",
|
83 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
84 |
},
|
85 |
+
"_n_updates": 492,
|
86 |
"n_steps": 1024,
|
87 |
"gamma": 0.999,
|
88 |
"gae_lambda": 0.98,
|
LunarLander-v2-PPO/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 sha256:98e9e787ce0aef6d81871b5b22275ea1ab021d326d72d6925abdb39fd77750b3
|
3 |
+
size 84893
|
LunarLander-v2-PPO/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5f0e11b3f3649e8c8a3cdab254081fc24e19e3d00279daaef1947133c1ad68c
|
3 |
size 43201
|
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: 256.70 +/- 15.77
|
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 0x7f394c0eda70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f394c0edb00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f394c0edb90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f394c0edc20>", "_build": "<function ActorCriticPolicy._build at 0x7f394c0edcb0>", "forward": "<function ActorCriticPolicy.forward at 0x7f394c0edd40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f394c0eddd0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f394c0ede60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f394c0edef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f394c0edf80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f394c0f2050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f394c142570>"}, "verbose": false, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652548021.4101498, "learning_rate": 0.0001, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8aNuLrHEMthZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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": 248, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7f444c21f0e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f444c21f170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f444c21f200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f444c21f290>", "_build": "<function ActorCriticPolicy._build at 0x7f444c21f320>", "forward": "<function ActorCriticPolicy.forward at 0x7f444c21f3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f444c21f440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f444c21f4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f444c21f560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f444c21f5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f444c21f680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f444c26b840>"}, "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": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652550516.0483027, "learning_rate": {":type:": "<class '__main__.Scheduler'>", ":serialized:": "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", "learning_rate": 2.506191890196153e-05, "decay": 0.99}, "tensorboard_log": null, "lr_schedule": {":type:": "<class '__main__.Scheduler'>", ":serialized:": "gAWVgwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwUX21ha2Vfc2tlbGV0b25fY2xhc3OUk5QojAhidWlsdGluc5SMBHR5cGWUk5SMCVNjaGVkdWxlcpRoA4wGb2JqZWN0lJOUhZR9lIwgOTc1ZDhjNGZmNDBmNDUxMzllY2YxYmRiMGRhZTdiMjmUTnSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjA9fY2xhc3Nfc2V0c3RhdGWUk5RoDX2UKIwKX19tb2R1bGVfX5SMCF9fbWFpbl9flIwIX19pbml0X1+UaACMDV9idWlsdGluX3R5cGWUk5SMCkxhbWJkYVR5cGWUhZRSlChoFowIQ29kZVR5cGWUhZRSlChLA0sASwNLAktDQxB8AXwAXwB8AnwAXwFkAFMAlE6FlIwNbGVhcm5pbmdfcmF0ZZSMBWRlY2F5lIaUjARzZWxmlGgfaCCHlIwfPGlweXRob24taW5wdXQtMTAtODJlZTE3OWRhZTFkPpRoFEsCQwQAAQYBlCkpdJRSlH2UKIwLX19wYWNrYWdlX1+UTowIX19uYW1lX1+UaBN1Tk5OdJRSlGgOjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoLH2UfZQoaCpoFIwMX19xdWFsbmFtZV9flIwSU2NoZWR1bGVyLl9faW5pdF9flIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+URz8zqSowVTJhRz/vrhR64UeuhpRoEmgTjAdfX2RvY19flE6MC19fY2xvc3VyZV9flE6MF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMIwIX19jYWxsX1+UaBkoaBwoSwJLAEsCSwNLQ0MWfAAEAGoAfABqATkAAgBfAHwAagBTAJROhZRoH2gghpRoImgfhpRoJGg/SwZDBAABEAGUKSl0lFKUaChOTk50lFKUaC5oSH2UfZQoaCpoP2gxjBJTY2hlZHVsZXIuX19jYWxsX1+UaDN9lGg1Tmg2TmgSaBNoOE5oOU5oOl2UaDx9lHWGlIZSMGg4TowNX19zbG90bmFtZXNfX5RdlHV9lIaUhlIwKYGUfZQoaB9HPvpHgfP0EERoIEc/764UeuFHrnViLg==", "learning_rate": 2.506191890196153e-05, "decay": 0.99}, "_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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 sha256:50486689dd50a30e1948e4937dca4be2c58ccbdec1d1d08df194e0a0289f3286
|
3 |
+
size 234746
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 256.70422000804786, "std_reward": 15.77447780951087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-14T18:23:38.330754"}
|