PPO / LunarLander-v2
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2-v_1_2.zip +2 -2
- ppo-LunarLander-v2-v_1_2/data +24 -24
- ppo-LunarLander-v2-v_1_2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2-v_1_2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 267.60 +/- 19.62
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param 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 0x7f5cdb054ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5cdb054d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5cdb054dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5cdb054e50>", "_build": "<function ActorCriticPolicy._build at 0x7f5cdb054ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f5cdb054f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5cdb05a040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5cdb05a0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5cdb05a160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5cdb05a1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5cdb05a280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5cdb051630>"}, "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": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1672057202892146149, "learning_rate": 0.00014, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAM29g7xxPRi5PrU5O2Iiejbrtxq7Q5ZbugAAgD8AAIA/JjjnvcPxXro77rw7wy3RN72yvLiTLNU1AAAAAAAAAABaYrI9rsYZP1mFpj3vyQ+/XQEBPqG1Gb0AAAAAAAAAAM0MKbyPKjq6+zQJO4L0QjYvbg87gAIfugAAgD8AAIA/sxxVPeyh0rntoi05/Vk8NsONLrumAUy4AACAPwAAgD+aBok9FHyCumnGKbp3mNWzmaDAuqiGQjkAAIA/AACAP1PZsT7T3RQ/hJwhPrmPQb8JfdA+4zlpPQAAAAAAAAAAAJ30vPZMHbrqBxe8z3IkObN2V7oF6ZO4AACAPwAAgD9mmlc8fP2zPyVnLD75FeG9Ni/6O47mxD0AAAAAAAAAACYXib171pC6mM2LO+K6yTX43Yy6/GihugAAgD8AAAAAGtUnvfYcLLoZXz87+5nLN5kqjDv7xg66AACAPwAAgD/NGM87w4FKuhbQPTy6dIw2P4VYutowiDUAAIA/AACAP5oBYz24huO5cSIXvEEQOjXqvLA6FpyptAAAgD8AAAAAmsFsvLhml7k/pKs7UZJjNu8od7rMusy6AACAPwAAgD/AzxS+zysdvGNxCb1O2YK761OAPR27WDwAAIA/AAAAAOZxAL0p9DS6P2+bujzKNbbkCDS7DNGxOQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1104, "n_steps": 1024, "gamma": 0.993, "gae_lambda": 0.98, "ent_coef": 0.043, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 6, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 0x7f717de56f70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f717de5b040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f717de5b0d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f717de5b160>", "_build": "<function ActorCriticPolicy._build at 0x7f717de5b1f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f717de5b280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f717de5b310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f717de5b3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f717de5b430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f717de5b4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f717de5b550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f717de555a0>"}, "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": 1672063924032102878, "learning_rate": 0.0002, "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": -0.007616000000000067, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2-v_1_2.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 sha256:0362df4e6659cf8a8dff639e29cd8fd79246b6b1f5aeadd242457d54877061e0
|
3 |
+
size 147098
|
ppo-LunarLander-v2-v_1_2/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": {},
|
@@ -42,21 +42,21 @@
|
|
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.
|
52 |
"tensorboard_log": null,
|
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'>",
|
@@ -66,24 +66,24 @@
|
|
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.
|
81 |
"gae_lambda": 0.98,
|
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:": "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"
|
|
|
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 0x7f717de56f70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f717de5b040>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f717de5b0d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f717de5b160>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f717de5b1f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f717de5b280>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f717de5b310>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f717de5b3a0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f717de5b430>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f717de5b4c0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f717de5b550>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f717de555a0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
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": 1672063924032102878,
|
51 |
+
"learning_rate": 0.0002,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.007616000000000067,
|
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": 492,
|
79 |
"n_steps": 1024,
|
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": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
ppo-LunarLander-v2-v_1_2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce80718817f2d34883c90cbd2ba120278693bd9ddf27edac0309d96d9ad3e522
|
3 |
size 87929
|
ppo-LunarLander-v2-v_1_2/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 sha256:1e2e688a84e0ca4da5cb5caa8becbf007ddb4e502fe0c909839f53146b31d31f
|
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": 267.59802090104006, "std_reward": 19.62435811455509, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-26T14:57:49.763798"}
|