Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2_lly.zip +3 -0
- ppo-LunarLander-v2_lly/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2_lly/data +95 -0
- ppo-LunarLander-v2_lly/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2_lly/policy.pth +3 -0
- ppo-LunarLander-v2_lly/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2_lly/system_info.txt +7 -0
- replay.mp4 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 247.66 +/- 13.92
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fe2abf3d310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe2abf3d3a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe2abf3d430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe2abf3d4c0>", "_build": "<function ActorCriticPolicy._build at 0x7fe2abf3d550>", "forward": "<function ActorCriticPolicy.forward at 0x7fe2abf3d5e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe2abf3d670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe2abf3d700>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe2abf3d790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe2abf3d820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe2abf3d8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe2abf3d940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fe2abf37870>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678207381998608890, "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": 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": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2_lly.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69160cab813a5b82b19e01c373c6c1549fe9145688d91d58c5e5fbc75a1f01ac
|
3 |
+
size 147424
|
ppo-LunarLander-v2_lly/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2_lly/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fe2abf3d310>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe2abf3d3a0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe2abf3d430>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe2abf3d4c0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fe2abf3d550>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fe2abf3d5e0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe2abf3d670>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe2abf3d700>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fe2abf3d790>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe2abf3d820>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe2abf3d8b0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe2abf3d940>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fe2abf37870>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
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 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1678207381998608890,
|
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": 248,
|
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:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null
|
95 |
+
}
|
ppo-LunarLander-v2_lly/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eacfd9497b78ca06071c132da8b99cc1c793f741a98a3d00aa61d2c00ee60cc
|
3 |
+
size 87929
|
ppo-LunarLander-v2_lly/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f254c58b18618aa0ace37635ef75af8909d213e63f280302107b59726f532c5
|
3 |
+
size 43393
|
ppo-LunarLander-v2_lly/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_lly/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (252 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 247.65770565384508, "std_reward": 13.921075859464516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-07T18:29:54.877019"}
|