first try ppo lunarlander
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: 229.46 +/- 87.13
|
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 0x7f0f7a889560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0f7a8895f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0f7a889680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0f7a889710>", "_build": "<function ActorCriticPolicy._build at 0x7f0f7a8897a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f0f7a889830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0f7a8898c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0f7a889950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0f7a8899e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0f7a889a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0f7a889b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f0f7a852960>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653605756.7595258, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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-5.4.188+-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:f46fedee590b413017ccc6f2c70aa62afaf9d77cf568e2f0f713a379897330ec
|
3 |
+
size 144144
|
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 0x7f0f7a889560>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0f7a8895f0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0f7a889680>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0f7a889710>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f0f7a8897a0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f0f7a889830>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0f7a8898c0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f0f7a889950>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0f7a8899e0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0f7a889a70>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0f7a889b00>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f0f7a852960>"
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653605756.7595258,
|
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": -0.015808000000000044,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a1510d07d2cb993057a471cf5d0588910a4296d8f226a1ffb83024dea9564cb
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5553c6a9511926d467db0e9063cfb253ca631290cf07e0d8b4798d05946519b1
|
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 sha256:82a6a506435ff8dfa566ff6504dd5a6a313e7e050afaf26b90bf7fb98d2d54c7
|
3 |
+
size 250676
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 229.45549855011524, "std_reward": 87.12614219071578, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-26T23:53:15.425403"}
|