marcin-sobocinski
commited on
Commit
•
c59a19e
1
Parent(s):
f2ccffe
First attempt PPO for LunarLander-v2
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +33 -21
- 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
@@ -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: 256.59 +/- 19.33
|
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 0x28bda9c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x28bda9ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x28bda9d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x28bda9dc0>", "_build": "<function ActorCriticPolicy._build at 0x28bda9e50>", "forward": "<function ActorCriticPolicy.forward at 0x28bda9ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x28bda9f70>", "_predict": "<function ActorCriticPolicy._predict at 0x28bdac040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x28bdac0d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x28bdac160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x28bdac1f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28bdaa740>"}, "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:": "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"}, "_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": "macOS-13.0.1-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 9 20:15:09 PDT 2022; root:xnu-8792.41.9~2/RELEASE_ARM64_T6000", "Python": "3.9.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0", "GPU Enabled": "False", "Numpy": "1.23.4", "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 0x15f8cae50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15f8caee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15f8caf70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15f8ce040>", "_build": "<function ActorCriticPolicy._build at 0x15f8ce0d0>", "forward": "<function ActorCriticPolicy.forward at 0x15f8ce160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15f8ce1f0>", "_predict": "<function ActorCriticPolicy._predict at 0x15f8ce280>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15f8ce310>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15f8ce3a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x15f8ce430>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x15f8cd980>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670402916240581000, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV9QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGIvVXNlcnMvc29ib2NpbnNraS9tYW1iYWZvcmdlL2VudnMvUkwvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYi9Vc2Vycy9zb2JvY2luc2tpL21hbWJhZm9yZ2UvZW52cy9STC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+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": "macOS-13.0.1-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 9 20:15:09 PDT 2022; root:xnu-8792.41.9~2/RELEASE_ARM64_T6000", "Python": "3.9.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0", "GPU Enabled": "False", "Numpy": "1.23.4", "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:ff52746bf0498286f2750667a383e27d8ed851148b1cdb50a1a7f3fb6e9bfdcd
|
3 |
+
size 146842
|
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._abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -42,28 +42,40 @@
|
|
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:": "gAWV9QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGIvVXNlcnMvc29ib2NpbnNraS9tYW1iYWZvcmdlL2VudnMvUkwvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYi9Vc2Vycy9zb2JvY2luc2tpL21hbWJhZm9yZ2UvZW52cy9STC9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
56 |
},
|
57 |
-
"_last_obs":
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
"_last_original_obs": null,
|
60 |
"_episode_num": 0,
|
61 |
"use_sde": false,
|
62 |
"sde_sample_freq": -1,
|
63 |
-
"_current_progress_remaining":
|
64 |
-
"ep_info_buffer":
|
65 |
-
|
66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"n_steps": 1024,
|
68 |
"gamma": 0.999,
|
69 |
"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 0x15f8cae50>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15f8caee0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15f8caf70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15f8ce040>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x15f8ce0d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x15f8ce160>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15f8ce1f0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x15f8ce280>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15f8ce310>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15f8ce3a0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x15f8ce430>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x15f8cd980>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670402916240581000,
|
51 |
"learning_rate": 0.0003,
|
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'>",
|
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": -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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"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 sha256:77d81fe6be03c0941c567956cfecbe2475e5d3aa4beb6d8b6fb9ebbbc83a614a
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43073
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:402090bf9204fdb5d988fbb204e7d37e9981364d81f35a4feed089edf9d1e43b
|
3 |
size 43073
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 256.5938261419441, "std_reward": 19.329754377019714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T09:59:27.920698"}
|