sophielang
commited on
Commit
•
da1bce7
1
Parent(s):
61567c0
Initial commit
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- sophie-ppo-LunarLander-v2.zip +3 -0
- sophie-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- sophie-ppo-LunarLander-v2/data +94 -0
- sophie-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- sophie-ppo-LunarLander-v2/policy.pth +3 -0
- sophie-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- sophie-ppo-LunarLander-v2/system_info.txt +7 -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: 254.96 +/- 21.01
|
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 0x7fd162e9bca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd162e9bd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd162e9bdc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd162e9be50>", "_build": "<function ActorCriticPolicy._build at 0x7fd162e9bee0>", "forward": "<function ActorCriticPolicy.forward at 0x7fd162e9bf70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd162e9f040>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd162e9f0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd162e9f160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd162e9f1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd162e9f280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd162e97480>"}, "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": 1671535258191368189, "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"}}
|
replay.mp4
ADDED
Binary file (220 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 254.96451816415706, "std_reward": 21.00781816678947, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T11:54:17.615616"}
|
sophie-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db6400129d78a2b0882249f7e3bcf75795b7bbd6b94c8e66ee03fe2ca863dcab
|
3 |
+
size 147206
|
sophie-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
sophie-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 0x7fd162e9bca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd162e9bd30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd162e9bdc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd162e9be50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd162e9bee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd162e9bf70>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd162e9f040>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd162e9f0d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd162e9f160>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd162e9f1f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd162e9f280>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fd162e97480>"
|
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": 1671535258191368189,
|
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 |
+
}
|
sophie-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d562fac55ddd31c4eb82f854498183d4e55d8de58a7ea09d482d2471d72c203
|
3 |
+
size 87929
|
sophie-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9793bbe1a5f8989950b3f983c07cd4411297d9112829e6baaf17dc40e89674b9
|
3 |
+
size 43201
|
sophie-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
|
sophie-ppo-LunarLander-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
|