jcgarciaca
commited on
Commit
•
1757722
1
Parent(s):
fc30704
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +18 -18
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
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: 238.25 +/- 47.46
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fcf02b19320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcf02b193b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcf02b19440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcf02b194d0>", "_build": "<function ActorCriticPolicy._build at 0x7fcf02b19560>", "forward": "<function ActorCriticPolicy.forward at 0x7fcf02b195f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcf02b19680>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcf02b19710>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcf02b197a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcf02b19830>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcf02b198c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcf02b63a20>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653353641.9530134, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f01447a7290>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01447a7320>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01447a73b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01447a7440>", "_build": "<function ActorCriticPolicy._build at 0x7f01447a74d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f01447a7560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01447a75f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f01447a7680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01447a7710>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01447a77a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01447a7830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f01447eea20>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu", "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653404711.486982, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "n_steps": 2048, "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": 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-5.4.188+-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"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f7a8bd833b8aedf3df6b4cd43f642d1655448575c340ee9f73bf09ecf812c63
|
3 |
+
size 144220
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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": 1,
|
22 |
"policy_kwargs": {},
|
@@ -47,7 +47,7 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "gASVjQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,21 +69,21 @@
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
-
"n_steps":
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
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:": "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"
|
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f01447a7290>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01447a7320>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01447a73b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01447a7440>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f01447a74d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f01447a7560>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01447a75f0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f01447a7680>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01447a7710>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01447a77a0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01447a7830>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f01447eea20>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1653404711.486982,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 310,
|
79 |
+
"n_steps": 2048,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
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:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cbfa0c7970e7688408e21f210957780ee7dc9bd2a86c0bfb97514337028d019
|
3 |
+
size 84893
|
ppo-LunarLander-v2/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:deddf7c8acc72ee08ca3b0666753b1aacc68a9ae6b2197043982f69607abb103
|
3 |
size 43201
|
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:ba709378a76f333d757bef72bef4f389312bcb27a1d449f10224f75d43951ed4
|
3 |
+
size 225636
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 238.24753519701207, "std_reward": 47.45785206578691, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-24T15:33:17.573696"}
|