upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- my-ppo-LunarLander-v2.zip +3 -0
- my-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- my-ppo-LunarLander-v2/data +92 -0
- my-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- my-ppo-LunarLander-v2/policy.pth +3 -0
- my-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- my-ppo-LunarLander-v2/system_info.txt +7 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: -16.50 +/- 57.79
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
config.json
ADDED
@@ -0,0 +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 0x7fa5e0ac75e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa5e0ac7670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa5e0ac7700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa5e0ac7790>", "_build": "<function ActorCriticPolicy._build at 0x7fa5e0ac7820>", "forward": "<function ActorCriticPolicy.forward at 0x7fa5e0ac78b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa5e0ac7940>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa5e0ac79d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa5e0ac7a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa5e0ac7af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa5e0ac7b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa5e0abda50>"}, "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": 507904, "_total_timesteps": 500000, "seed": null, "action_noise": null, "start_time": 1652451600.446371, "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": -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": 124, "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:": "gAWV+wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGUvaG9tZS90b2J5L3Byb2plY3RzL2RlZXAtcmwtY2xhc3MvLnZlbnYvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMZS9ob21lL3RvYnkvcHJvamVjdHMvZGVlcC1ybC1jbGFzcy8udmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.10.60.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 #1 SMP Wed Aug 25 23:20:18 UTC 2021", "Python": "3.8.10", "Stable-Baselines3": "1.3.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.19.0"}}
|
my-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c66410283de06b283425ee4e1970ab4569d161f8af83735137e19345e5d7ff1
|
3 |
+
size 144149
|
my-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.3.0
|
my-ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7fa5e0ac75e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa5e0ac7670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa5e0ac7700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa5e0ac7790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fa5e0ac7820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fa5e0ac78b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa5e0ac7940>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fa5e0ac79d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa5e0ac7a60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa5e0ac7af0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa5e0ac7b80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fa5e0abda50>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=",
|
39 |
+
"n": 4,
|
40 |
+
"shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"seed": null,
|
48 |
+
"action_noise": null,
|
49 |
+
"start_time": 1652451600.446371,
|
50 |
+
"learning_rate": 0.0003,
|
51 |
+
"tensorboard_log": null,
|
52 |
+
"lr_schedule": {
|
53 |
+
":type:": "<class 'function'>",
|
54 |
+
":serialized:": "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"
|
55 |
+
},
|
56 |
+
"_last_obs": {
|
57 |
+
":type:": "<class 'numpy.ndarray'>",
|
58 |
+
":serialized:": "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"
|
59 |
+
},
|
60 |
+
"_last_episode_starts": {
|
61 |
+
":type:": "<class 'numpy.ndarray'>",
|
62 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
63 |
+
},
|
64 |
+
"_last_original_obs": null,
|
65 |
+
"_episode_num": 0,
|
66 |
+
"use_sde": false,
|
67 |
+
"sde_sample_freq": -1,
|
68 |
+
"_current_progress_remaining": -0.015808000000000044,
|
69 |
+
"ep_info_buffer": {
|
70 |
+
":type:": "<class 'collections.deque'>",
|
71 |
+
":serialized:": "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"
|
72 |
+
},
|
73 |
+
"ep_success_buffer": {
|
74 |
+
":type:": "<class 'collections.deque'>",
|
75 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
76 |
+
},
|
77 |
+
"_n_updates": 124,
|
78 |
+
"n_steps": 1024,
|
79 |
+
"gamma": 0.999,
|
80 |
+
"gae_lambda": 0.98,
|
81 |
+
"ent_coef": 0.01,
|
82 |
+
"vf_coef": 0.5,
|
83 |
+
"max_grad_norm": 0.5,
|
84 |
+
"batch_size": 64,
|
85 |
+
"n_epochs": 4,
|
86 |
+
"clip_range": {
|
87 |
+
":type:": "<class 'function'>",
|
88 |
+
":serialized:": "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"
|
89 |
+
},
|
90 |
+
"clip_range_vf": null,
|
91 |
+
"target_kl": null
|
92 |
+
}
|
my-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f6298055beb773f54fc2ca0c59a06bf2aa446e977542a73492c000c15060922
|
3 |
+
size 84829
|
my-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd9655805b3882571d84e51c1993297012b4b6691ab7cef332a6dc2a6254f5bb
|
3 |
+
size 43201
|
my-ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
my-ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.60.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 #1 SMP Wed Aug 25 23:20:18 UTC 2021
|
2 |
+
Python: 3.8.10
|
3 |
+
Stable-Baselines3: 1.3.0
|
4 |
+
PyTorch: 1.11.0+cu102
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.22.3
|
7 |
+
Gym: 0.19.0
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2f625b91a079761ee6725c46ce04cd862d8f1f1ae01aa9a2b566911aa9612a5
|
3 |
+
size 143890
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.2.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7feaa32515e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7feaa3251670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7feaa3251700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7feaa3251790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7feaa3251820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7feaa32518b0>",
|
13 |
+
"_get_latent": "<function ActorCriticPolicy._get_latent at 0x7feaa3251940>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7feaa32519d0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7feaa3251a60>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7feaa3251af0>",
|
17 |
+
"__abstractmethods__": "frozenset()",
|
18 |
+
"_abc_impl": "<_abc_data object at 0x7feaa324f3c0>"
|
19 |
+
},
|
20 |
+
"verbose": 1,
|
21 |
+
"policy_kwargs": {},
|
22 |
+
"observation_space": {
|
23 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
24 |
+
":serialized:": "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",
|
25 |
+
"dtype": "float32",
|
26 |
+
"bounded_below": "[False False False False False False False False]",
|
27 |
+
"bounded_above": "[False False False False False False False False]",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"low_repr": "-inf",
|
34 |
+
"high_repr": "inf",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVjAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lGgIk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
|
40 |
+
"n": 4,
|
41 |
+
"start": 0,
|
42 |
+
"_shape": [],
|
43 |
+
"dtype": "int64",
|
44 |
+
"_np_random": null
|
45 |
+
},
|
46 |
+
"n_envs": 16,
|
47 |
+
"num_timesteps": 1015808,
|
48 |
+
"_total_timesteps": 1000000,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1652450157.894573,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 372,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "gAWV+wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGUvaG9tZS90b2J5L3Byb2plY3RzL2RlZXAtcmwtY2xhc3MvLnZlbnYvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS31DAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMZS9ob21lL3RvYnkvcHJvamVjdHMvZGVlcC1ybC1jbGFzcy8udmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16650a091695ea42d31c2433e376b2413f1f49c623b95bfd0887095958932dd1
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:094a6e1872f7b83e8e484a59986009073d1455e7122ea44611c33b082df3b465
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6080938434e7cbd15dee6263a8e92a189075098d8531178f43eef1d602fa93c9
|
3 |
+
size 284100
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -16.497897369543352, "std_reward": 57.79133704892941, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T22:31:16.189889"}
|