brandonbrule
commited on
Commit
•
44d5ccd
1
Parent(s):
124c146
Push LunarLander-v2 Model
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LundarLander-v2.zip +3 -0
- ppo-LundarLander-v2/_stable_baselines3_version +1 -0
- ppo-LundarLander-v2/data +94 -0
- ppo-LundarLander-v2/policy.optimizer.pth +3 -0
- ppo-LundarLander-v2/policy.pth +3 -0
- ppo-LundarLander-v2/pytorch_variables.pth +3 -0
- ppo-LundarLander-v2/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: 248.69 +/- 18.71
|
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 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 0x7faeda2845e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faeda284670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faeda284700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faeda284790>", "_build": "<function ActorCriticPolicy._build at 0x7faeda284820>", "forward": "<function ActorCriticPolicy.forward at 0x7faeda2848b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faeda284940>", "_predict": "<function ActorCriticPolicy._predict at 0x7faeda2849d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faeda284a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faeda284af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faeda284b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7faeda2fbe70>"}, "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:": "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": 1670692904718731150, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LundarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93de7bac2077369129aced185164085d402472621d2df98ab84c83bf12d0c806
|
3 |
+
size 147214
|
ppo-LundarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
ppo-LundarLander-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 0x7faeda2845e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faeda284670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faeda284700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faeda284790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7faeda284820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7faeda2848b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faeda284940>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7faeda2849d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faeda284a60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faeda284af0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7faeda284b80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7faeda2fbe70>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1670692904718731150,
|
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": 248,
|
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-LundarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbbcbce4459834a1674e9d19ad1810c8d22d23cae5e82716cf64353e19ca663a
|
3 |
+
size 87929
|
ppo-LundarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab5e7961256c68f42040786f8026b08f3567b86075c516ce4ea8b7e9009ba6a
|
3 |
+
size 43201
|
ppo-LundarLander-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-LundarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (233 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 248.68942523265224, "std_reward": 18.714880911341357, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T18:16:15.986518"}
|