shoaibahmed
commited on
Commit
•
48e6ce0
1
Parent(s):
ad2950a
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -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
- 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: 251.88 +/- 24.29
|
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 0x7f9049966a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9049966af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9049966b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9049966c10>", "_build": "<function ActorCriticPolicy._build at 0x7f9049966ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9049966d30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9049966dc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9049966e50>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9049966ee0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9049966f70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9049968040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f90499680d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f90499624b0>"}, "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": 1673721524308001943, "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-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb95ca5e2bc4978edd03bd9e16c8e16109a89eb82ac7a76a48b7b98f748c3c72
|
3 |
+
size 147416
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f9049966a60>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9049966af0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9049966b80>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9049966c10>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9049966ca0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9049966d30>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9049966dc0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9049966e50>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9049966ee0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9049966f70>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9049968040>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f90499680d0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f90499624b0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1673721524308001943,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null
|
95 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:138bab320bf44bb69bd663c2bb6da38a0c672b148f892b7d65709892f6012900
|
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:e5893fd58e0dcc76d6acf8db024af3eb94e32aa8b846820ffeee2cc357823c1d
|
3 |
+
size 43393
|
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-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.16
|
3 |
+
- Stable-Baselines3: 1.7.0
|
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 (207 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 251.87512819719456, "std_reward": 24.293989831557095, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-14T18:58:46.864670"}
|