Second attempt using settting provided in example
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -33
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- 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: -514.44 +/- 131.85
|
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 0x7f15372f8200>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f15372f8290>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f15372f8320>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f15372f83b0>", "_build": "<function ActorCriticPolicy._build at 0x7f15372f8440>", "forward": "<function ActorCriticPolicy.forward at 0x7f15372f84d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f15372f8560>", "_predict": "<function ActorCriticPolicy._predict at 0x7f15372f85f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f15372f8680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f15372f8710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f15372f87a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f153734b210>"}, "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": 16384, "_total_timesteps": 2000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1660413472.492055, "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": -7.192, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "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": "1.6.0", "PyTorch": "1.12.1+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 0x7f18b7a81320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f18b7a813b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f18b7a81440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f18b7a814d0>", "_build": "<function ActorCriticPolicy._build at 0x7f18b7a81560>", "forward": "<function ActorCriticPolicy.forward at 0x7f18b7a815f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f18b7a81680>", "_predict": "<function ActorCriticPolicy._predict at 0x7f18b7a81710>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f18b7a817a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f18b7a81830>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f18b7a818c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f18b7a46ba0>"}, "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": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": "1.6.0", "PyTorch": "1.12.1+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:e5e96b3ab8a14d6905aa051a2b5417f587221bf233a86834ae089702040a829b
|
3 |
+
size 52800
|
ppo-LunarLander-v2/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_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -42,40 +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": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
":serialized:": "gAWVwQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
56 |
},
|
57 |
-
"_last_obs":
|
58 |
-
|
59 |
-
":serialized:": "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"
|
60 |
-
},
|
61 |
-
"_last_episode_starts": {
|
62 |
-
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
-
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining":
|
70 |
-
"ep_info_buffer":
|
71 |
-
|
72 |
-
|
73 |
-
},
|
74 |
-
"ep_success_buffer": {
|
75 |
-
":type:": "<class 'collections.deque'>",
|
76 |
-
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
-
},
|
78 |
-
"_n_updates": 4,
|
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 0x7f18b7a81320>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f18b7a813b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f18b7a81440>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f18b7a814d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f18b7a81560>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f18b7a815f0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f18b7a81680>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f18b7a81710>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f18b7a817a0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f18b7a81830>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f18b7a818c0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f18b7a46ba0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 0,
|
46 |
+
"_total_timesteps": 0,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": null,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
":serialized:": "gAWVwQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
56 |
},
|
57 |
+
"_last_obs": null,
|
58 |
+
"_last_episode_starts": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
"_last_original_obs": null,
|
60 |
"_episode_num": 0,
|
61 |
"use_sde": false,
|
62 |
"sde_sample_freq": -1,
|
63 |
+
"_current_progress_remaining": 1,
|
64 |
+
"ep_info_buffer": null,
|
65 |
+
"ep_success_buffer": null,
|
66 |
+
"_n_updates": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"n_steps": 1024,
|
68 |
"gamma": 0.999,
|
69 |
"gae_lambda": 0.98,
|
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 sha256:8f5c3a8a9cf8723484290c4a4cb433ff4a9014f3287ff216c7473a561603123f
|
3 |
+
size 623
|
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 sha256:87a489319943dc56b43b27f8888591d951f82509c7ad7ecb663133446696d07c
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -514.4435872912406, "std_reward": 131.84717331976074, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-13T20:56:35.702996"}
|