Initial commit
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- my_little_perceptron_rl.zip +3 -0
- my_little_perceptron_rl/_stable_baselines3_version +1 -0
- my_little_perceptron_rl/data +91 -0
- my_little_perceptron_rl/policy.optimizer.pth +3 -0
- my_little_perceptron_rl/policy.pth +3 -0
- my_little_perceptron_rl/pytorch_variables.pth +3 -0
- my_little_perceptron_rl/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 149.42 +/- 111.62
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f3bca8bc170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3bca8bc200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3bca8bc290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3bca8bc320>", "_build": "<function ActorCriticPolicy._build at 0x7f3bca8bc3b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3bca8bc440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3bca8bc4d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3bca8bc560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3bca8bc5f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3bca8bc680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3bca8bc710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3bca9087b0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653220700.6098459, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 160, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
my_little_perceptron_rl.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10ca8cb5419daa78d487e7b0702a2b2b01f41c5104c0dd5a9dc45e6a05cc82d7
|
3 |
+
size 143243
|
my_little_perceptron_rl/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
my_little_perceptron_rl/data
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f3bca8bc170>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3bca8bc200>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3bca8bc290>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3bca8bc320>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3bca8bc3b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3bca8bc440>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3bca8bc4d0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3bca8bc560>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3bca8bc5f0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3bca8bc680>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3bca8bc710>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f3bca9087b0>"
|
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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 524288,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653220700.6098459,
|
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": null,
|
58 |
+
"_last_episode_starts": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
61 |
+
},
|
62 |
+
"_last_original_obs": null,
|
63 |
+
"_episode_num": 0,
|
64 |
+
"use_sde": false,
|
65 |
+
"sde_sample_freq": -1,
|
66 |
+
"_current_progress_remaining": -0.04857599999999995,
|
67 |
+
"ep_info_buffer": {
|
68 |
+
":type:": "<class 'collections.deque'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"ep_success_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
74 |
+
},
|
75 |
+
"_n_updates": 160,
|
76 |
+
"n_steps": 2048,
|
77 |
+
"gamma": 0.99,
|
78 |
+
"gae_lambda": 0.95,
|
79 |
+
"ent_coef": 0.0,
|
80 |
+
"vf_coef": 0.5,
|
81 |
+
"max_grad_norm": 0.5,
|
82 |
+
"batch_size": 64,
|
83 |
+
"n_epochs": 10,
|
84 |
+
"clip_range": {
|
85 |
+
":type:": "<class 'function'>",
|
86 |
+
":serialized:": "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"
|
87 |
+
},
|
88 |
+
"clip_range_vf": null,
|
89 |
+
"normalize_advantage": true,
|
90 |
+
"target_kl": null
|
91 |
+
}
|
my_little_perceptron_rl/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a183e0280d632be1c36cd677e4cd66683ce2f8a46672fa9c569a7e07c444092
|
3 |
+
size 84893
|
my_little_perceptron_rl/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2645851d656e207dd929a5f2fd85e12b1ce0c5031a8aa6308c4d69d6b43d160e
|
3 |
+
size 43201
|
my_little_perceptron_rl/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
my_little_perceptron_rl/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:151a49a4099446d599c52b86cfe8fd2dfd38419a7108cde48c91a8ddb98374f6
|
3 |
+
size 246133
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 149.42009427880498, "std_reward": 111.61562239959052, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T12:34:15.455096"}
|