naveenk903
commited on
Commit
•
6b7b728
1
Parent(s):
dbcfb11
Upload PPO LunarLander-v2 trained agent new
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -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 +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: 237.66 +/- 43.74
|
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 0x7fa422a69b00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa422a69b90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa422a69c20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa422a69cb0>", "_build": "<function ActorCriticPolicy._build at 0x7fa422a69d40>", "forward": "<function ActorCriticPolicy.forward at 0x7fa422a69dd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa422a69e60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa422a69ef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa422a69f80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa422a6f050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa422a6f0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa422ab4a80>"}, "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": 311296, "_total_timesteps": 300000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1654690985.4636068, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.037653333333333316, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 256, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 8, "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"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5055cfb14a95d723b32a5ab3d9ec067d6fd64e032b6646030fcc4f71b68dff98
|
3 |
+
size 144203
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fa422a69b00>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa422a69b90>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa422a69c20>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa422a69cb0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fa422a69d40>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fa422a69dd0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa422a69e60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fa422a69ef0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa422a69f80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa422a6f050>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa422a6f0e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fa422ab4a80>"
|
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": 311296,
|
46 |
+
"_total_timesteps": 300000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1654690985.4636068,
|
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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.037653333333333316,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 256,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 32,
|
86 |
+
"n_epochs": 8,
|
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-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ef6835a1f8e8d3daed3f1c0a7dd9d27a6b95d673cff69333b4ae422f775416
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6020a2b21593349c915253aa1431a2ab385c53012e478c3230cef84ce16e546
|
3 |
+
size 43201
|
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-5.4.188+-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 sha256:58813e57c507cb0f1feb8371bafc3d44e7506d1b47b2adb85bd639a3d1dfeca9
|
3 |
+
size 221026
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 237.65728220420038, "std_reward": 43.7424007731245, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-08T12:36:57.572059"}
|