Upload PPO LunarLander-v2 trained agent
Browse files- LunarLander_PPO_agent.zip +3 -0
- LunarLander_PPO_agent/_stable_baselines3_version +1 -0
- LunarLander_PPO_agent/data +94 -0
- LunarLander_PPO_agent/policy.optimizer.pth +3 -0
- LunarLander_PPO_agent/policy.pth +3 -0
- LunarLander_PPO_agent/pytorch_variables.pth +3 -0
- LunarLander_PPO_agent/system_info.txt +7 -0
- README.md +34 -1
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander_PPO_agent.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:649121036b45bcc7c58cb2faa42663037523cabc0aebc92797c8c352aee089ec
|
3 |
+
size 146278
|
LunarLander_PPO_agent/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.0
|
LunarLander_PPO_agent/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 0x7f58f55c4a70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f58f55c4b00>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f58f55c4b90>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f58f55c4c20>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f58f55c4cb0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f58f55c4d40>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f58f55c4dd0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f58f55c4e60>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f58f55c4ef0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f58f55c4f80>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f58f55c9050>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f58f5610b10>"
|
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": 1,
|
45 |
+
"num_timesteps": 800768,
|
46 |
+
"_total_timesteps": 800000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1659968430.5606837,
|
51 |
+
"learning_rate": 0.01,
|
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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEDbtr40RmI/ssJSvt67VL6b1Ii9oEDZPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0009600000000000719,
|
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": 3910,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 10,
|
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 |
+
}
|
LunarLander_PPO_agent/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6af051c8c08c752f6698235578a3836b469af5ca2bc4a75341efc4051a552adb
|
3 |
+
size 87993
|
LunarLander_PPO_agent/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:769ec4e988d27868f6f1e690221da9e218f87bec08ebace582c0911be712f956
|
3 |
+
size 43201
|
LunarLander_PPO_agent/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander_PPO_agent/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: 1.6.0
|
4 |
+
PyTorch: 1.12.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
README.md
CHANGED
@@ -1,3 +1,36 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 116.10 +/- 113.40
|
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:": "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 0x7f58f55c4a70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f58f55c4b00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f58f55c4b90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f58f55c4c20>", "_build": "<function ActorCriticPolicy._build at 0x7f58f55c4cb0>", "forward": "<function ActorCriticPolicy.forward at 0x7f58f55c4d40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f58f55c4dd0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f58f55c4e60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f58f55c4ef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f58f55c4f80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f58f55c9050>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f58f5610b10>"}, "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": 1, "num_timesteps": 800768, "_total_timesteps": 800000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659968430.5606837, "learning_rate": 0.01, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEDbtr40RmI/ssJSvt67VL6b1Ii9oEDZPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0009600000000000719, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3910, "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": "1.6.0", "PyTorch": "1.12.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (256 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 116.09864654449231, "std_reward": 113.39826383617564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-08T15:15:09.340566"}
|