Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -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
- ppo-LunarLander-v2/system_info.txt +7 -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: 204.65 +/- 31.76
|
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 0x7fbb45a61b00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbb45a61b90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbb45a61c20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbb45a61cb0>", "_build": "<function ActorCriticPolicy._build at 0x7fbb45a61d40>", "forward": "<function ActorCriticPolicy.forward at 0x7fbb45a61dd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbb45a61e60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbb45a61ef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbb45a61f80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbb45a66050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbb45a660e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbb45a34630>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651676430.2336633, "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:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-Ubuntu-20.04-focal #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.1a5", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4cd2c1b15b794a80a7b7f34a00c7559f26778094bcd813863b39166f6a63fd
|
3 |
+
size 144259
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a5
|
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 0x7fbb45a61b00>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbb45a61b90>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbb45a61c20>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbb45a61cb0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fbb45a61d40>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fbb45a61dd0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbb45a61e60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fbb45a61ef0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbb45a61f80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbb45a66050>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbb45a660e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fbb45a34630>"
|
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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
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 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651676430.2336633,
|
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": 124,
|
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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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
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 sha256:2a409d4ce1eb33e150b404503620671d8f5a49018485c6bee76e09bd9c7397f1
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:079def7563cbb18a1784497d7bf85c2cbdba21c4221c93c5c4d2165a3692a3f0
|
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
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-40-generic-x86_64-with-Ubuntu-20.04-focal #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.1a5
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8807b231e665894f7731389a0d21f99af1daf54d56399d1107775ae3d6de231f
|
3 |
+
size 246851
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 204.650167259325, "std_reward": 31.75673304367788, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-04T18:10:18.216638"}
|