Push Lunar Lander-v2 to the hub to the hub
Browse files- PPO_LunarLander-v2.zip +3 -0
- PPO_LunarLander-v2/_stable_baselines3_version +1 -0
- PPO_LunarLander-v2/data +96 -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
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO_LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32a2a56c87f190f03aa0dc85dd70ac12d0e51df67e0998e1629cd44900cdf35e
|
3 |
+
size 147395
|
PPO_LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
PPO_LunarLander-v2/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f513f45dee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f513f45df70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f513f461040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f513f4610d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f513f461160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f513f4611f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f513f461280>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f513f461310>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f513f4613a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f513f461430>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f513f4614c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f513f461550>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f513f462500>"
|
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": 1682293049397438626,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -0.015808000000000044,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 248,
|
59 |
+
"observation_space": {
|
60 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
61 |
+
":serialized:": "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",
|
62 |
+
"dtype": "float32",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
68 |
+
"bounded_below": "[False False False False False False False False]",
|
69 |
+
"bounded_above": "[False False False False False False False False]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
74 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
75 |
+
"n": 4,
|
76 |
+
"_shape": [],
|
77 |
+
"dtype": "int64",
|
78 |
+
"_np_random": null
|
79 |
+
},
|
80 |
+
"n_envs": 16,
|
81 |
+
"n_steps": 1024,
|
82 |
+
"gamma": 0.999,
|
83 |
+
"gae_lambda": 0.98,
|
84 |
+
"ent_coef": 0.01,
|
85 |
+
"vf_coef": 0.5,
|
86 |
+
"max_grad_norm": 0.5,
|
87 |
+
"batch_size": 64,
|
88 |
+
"n_epochs": 4,
|
89 |
+
"clip_range": {
|
90 |
+
":type:": "<class 'function'>",
|
91 |
+
":serialized:": "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"
|
92 |
+
},
|
93 |
+
"clip_range_vf": null,
|
94 |
+
"normalize_advantage": true,
|
95 |
+
"target_kl": null
|
96 |
+
}
|
PPO_LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b2c9c52b07e24bb4f0f8a63eec1ebb6204646a83b4435f2780501319a9386c1
|
3 |
+
size 87929
|
PPO_LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:869475cd6540ed25c067334a18af3fb456cfe97aba22c8eab93a0350331f17dd
|
3 |
+
size 43329
|
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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
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: 258.87 +/- 17.71
|
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 0x7f513f45dee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f513f45df70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f513f461040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f513f4610d0>", "_build": "<function ActorCriticPolicy._build at 0x7f513f461160>", "forward": "<function ActorCriticPolicy.forward at 0x7f513f4611f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f513f461280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f513f461310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f513f4613a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f513f461430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f513f4614c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f513f461550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f513f462500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682293049397438626, "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, "_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": 248, "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:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (239 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 258.8666013009905, "std_reward": 17.706818455657473, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-24T00:18:52.967099"}
|