Upload best PPO LunarLander-v2 agent (tuned with Optuna).
Browse files- .gitattributes +1 -0
- LunarLander-v2-PPO-optuna.zip +3 -0
- LunarLander-v2-PPO-optuna/_stable_baselines3_version +1 -0
- LunarLander-v2-PPO-optuna/data +94 -0
- LunarLander-v2-PPO-optuna/policy.optimizer.pth +3 -0
- LunarLander-v2-PPO-optuna/policy.pth +3 -0
- LunarLander-v2-PPO-optuna/pytorch_variables.pth +3 -0
- LunarLander-v2-PPO-optuna/system_info.txt +7 -0
- README.md +36 -0
- config.json +1 -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
|
LunarLander-v2-PPO-optuna.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a08327a514c4ad240fa11558182fddd086cb9284dbcc825e8617f9a7a6acd5fd
|
3 |
+
size 144028
|
LunarLander-v2-PPO-optuna/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
LunarLander-v2-PPO-optuna/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 0x7f02d1c8a3b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f02d1c8a440>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f02d1c8a4d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f02d1c8a560>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f02d1c8a5f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f02d1c8a680>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f02d1c8a710>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f02d1c8a7a0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f02d1c8a830>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f02d1c8a8c0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f02d1c8a950>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f02d1cd9660>"
|
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": 16384,
|
46 |
+
"_total_timesteps": 620,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1654990215.7161713,
|
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////9LAHSUYolDEAAAAAAAAQAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -25.425806451612903,
|
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": 4,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.994480666324143,
|
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 |
+
}
|
LunarLander-v2-PPO-optuna/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d93ec3b8168c774e960e092a1a730100c5b7ee7fce3f9b505efb3bed2d15959
|
3 |
+
size 84829
|
LunarLander-v2-PPO-optuna/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f4871f02f5066c53929204348753e41af53e0d39e0341420fdcef3fce2de3ef
|
3 |
+
size 43201
|
LunarLander-v2-PPO-optuna/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-v2-PPO-optuna/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
|
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: -170.80 +/- 74.73
|
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 0x7f02d1c8a3b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f02d1c8a440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f02d1c8a4d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f02d1c8a560>", "_build": "<function ActorCriticPolicy._build at 0x7f02d1c8a5f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f02d1c8a680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f02d1c8a710>", "_predict": "<function ActorCriticPolicy._predict at 0x7f02d1c8a7a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f02d1c8a830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f02d1c8a8c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f02d1c8a950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f02d1cd9660>"}, "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": 16384, "_total_timesteps": 620, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1654990215.7161713, "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////9LAHSUYolDEAAAAAAAAQAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -25.425806451612903, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "n_steps": 1024, "gamma": 0.994480666324143, "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"}}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a539f159a58c1bfcdde93c5a27c7e7c50b0bdc70d92a1ab28c706874f9054c9
|
3 |
+
size 204665
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -170.8020033022214, "std_reward": 74.72659532303398, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-11T23:30:42.914432"}
|