Push LunarLander-v2 model
Browse files- .gitattributes +1 -0
- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +99 -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 +9 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
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: 262.47 +/- 18.83
|
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 0x7fe35bfac860>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe35bfac900>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe35bfac9a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe35bfaca40>", "_build": "<function ActorCriticPolicy._build at 0x7fe35bfacae0>", "forward": "<function ActorCriticPolicy.forward at 0x7fe35bfacb80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe35bfacc20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe35bfaccc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe35bfacd60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe35bface00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe35bfacea0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe35bfacf40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe35bf10b40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1741195362655617958, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c7a2c995b196666a98375ff494a3b58073c1300218af2c5ab6a5cae496c31e4
|
3 |
+
size 148132
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fe35bfac860>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe35bfac900>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe35bfac9a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe35bfaca40>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fe35bfacae0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fe35bfacb80>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe35bfacc20>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe35bfaccc0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fe35bfacd60>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe35bface00>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe35bfacea0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe35bfacf40>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fe35bf10b40>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1741195362655617958,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 124,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
+
"n_steps": 2048,
|
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 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:511f23ee5cd7498c4c66f72d15c4e68d574ff1c323eb10d7e411545f8baca2ea
|
3 |
+
size 88362
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9478cec3a87c8b5ada766d417b2d955b65c195d88f19dc7fa2b76474996f4c3f
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
2 |
+
- Python: 3.11.11
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.5.1+cu124
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 3.1.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d81ca63e4ea36c4462161759dfcf4f88178c3a626a48cc53e55bd50202c0f2c
|
3 |
+
size 189379
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 262.4703912, "std_reward": 18.83106842688193, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-05T18:01:49.976044"}
|