salil-malhotra
commited on
Commit
•
497789f
1
Parent(s):
b9018f3
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +2 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- 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
|
@@ -21,6 +21,7 @@ model-index:
|
|
21 |
---
|
22 |
|
23 |
|
|
|
24 |
# **PPO** Agent playing **LunarLander-v2**
|
25 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 156.20 +/- 85.34
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
21 |
---
|
22 |
|
23 |
|
24 |
+
|
25 |
# **PPO** Agent playing **LunarLander-v2**
|
26 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
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 0x000001895FED0700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001895FED0790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001895FED0820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001895FED08B0>", "_build": "<function ActorCriticPolicy._build at 0x000001895FED0940>", "forward": "<function ActorCriticPolicy.forward at 0x000001895FED09D0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001895FED0A60>", "_predict": "<function ActorCriticPolicy._predict at 0x000001895FED0AF0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001895FED0B80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001895FED0C10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001895FED0CA0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x000001895FED20F0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVngEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBXNoYXBllEsIhZSMA2xvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lGgKSwiFlIwBQ5R0lFKUjARoaWdolGgSKJYgAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lGgKSwiFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWCAAAAAAAAAAAAAAAAAAAAJRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZRoFXSUUpSMDWJvdW5kZWRfYWJvdmWUaBIolggAAAAAAAAAAAAAAAAAAACUaCFLCIWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "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": 1652153113.2687364, "learning_rate": 0.0003, "tensorboard_log": "tmp/", "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 186, "n_steps": 2048, "gamma": 0.995, "gae_lambda": 0.99, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 48, "n_epochs": 6, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.18362-SP0 10.0.18362", "Python": "3.8.8", "Stable-Baselines3": "1.4.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.20.1", "Gym": "0.19.0"}}
|
|
|
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 0x0000012B49ED34C0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000012B49ED3550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000012B49ED35E0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000012B49ED3670>", "_build": "<function ActorCriticPolicy._build at 0x0000012B49ED3700>", "forward": "<function ActorCriticPolicy.forward at 0x0000012B49ED3790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000012B49ED3820>", "_predict": "<function ActorCriticPolicy._predict at 0x0000012B49ED38B0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000012B49ED3940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000012B49ED39D0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000012B49ED3A60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x0000012B49ED2180>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652209880.4233577, "learning_rate": 0.0002, "tensorboard_log": "tmp/", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAIDK6D2Fk6W58+gXvBGomrq7dUg7DD2SuwAAAAAAAIA/TcoGPQIBsj+NDSE+pLKAvo8AXjzSJ8w9AAAAAAAAAAAz+748j8oDui1TQjw2BM68+t6AuwTLGr0AAAAAAAAAAC3+LT4KuKg/Xh7/PltF/77+8yE+3FsXPgAAAAAAAAAAAHqtPezR/7lsJoi7BsM5ubFLgbsL6Kw4AACAPwAAgD/987i+j5VCP7BnuD3dvBq/fme/vnyBkz4AAAAAAAAAADPTzzrwT4s+Tj4+PkAp57497tI8W13UPQAAAAAAAAAAZp6svOHa/jlmNMc7ZXqDNqm+DrvUfI41AACAPwAAgD+AM/291Ii3P2KBJb/8cR6+skL3vYhJ374AAAAAAAAAAIDvpD5RiRm9RY75vPc8KrwlNEq+kDP5OgAAgD8AAIA/mvpBPZHDpT+uhY4+0Yb/vhvbXD00EhE+AAAAAAAAAACmfqc9sA2dP1OF+j4ekBi/parhvHxgTD0AAAAAAAAAAFqAnz1c/0i6kjblPBZmL72r6p27qO0GvQAAAAAAAAAAoLHPPiT1X70jafs9pYkmvg2Rib3RyoY/AACAPwAAAAADB9w+4UwRvQQvoz0M7BM7fvxtvVxWDz0AAIA/AACAP2Y57DzhVsq8laYKvZQagD0U/Y68oFOivAAAgD8AAIA/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": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 96, "n_steps": 2048, "gamma": 0.9995, "gae_lambda": 0.99, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 48, "n_epochs": 6, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.18362-SP0 10.0.18362", "Python": "3.8.8", "Stable-Baselines3": "1.4.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.20.1", "Gym": "0.19.0"}}
|
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 sha256:253e46704382db1844bff1b4992ff94713bc2ad0c7a9520fc4ff0f0ec338b207
|
3 |
+
size 143470
|
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": {},
|
@@ -42,21 +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": "tmp/",
|
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'>",
|
@@ -66,18 +66,18 @@
|
|
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": 2048,
|
80 |
-
"gamma": 0.
|
81 |
"gae_lambda": 0.99,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
|
|
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 0x0000012B49ED34C0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000012B49ED3550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000012B49ED35E0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000012B49ED3670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x0000012B49ED3700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x0000012B49ED3790>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000012B49ED3820>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x0000012B49ED38B0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000012B49ED3940>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000012B49ED39D0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x0000012B49ED3A60>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x0000012B49ED2180>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 524288,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652209880.4233577,
|
51 |
+
"learning_rate": 0.0002,
|
52 |
"tensorboard_log": "tmp/",
|
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": -0.04857599999999995,
|
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": 96,
|
79 |
"n_steps": 2048,
|
80 |
+
"gamma": 0.9995,
|
81 |
"gae_lambda": 0.99,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
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 84637
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9c58a4ec9b2e42697a4a986b561b56c90b30e930476f0caea793d70081fe564
|
3 |
size 84637
|
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 sha256:85d93a29edabed9778779613e904fe245e5e9d3dc02e8bf57417e7e32a19f13c
|
3 |
size 43073
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 156.20404110377777, "std_reward": 85.34149716378923, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T15:20:09.300409"}
|