Upload PPO LunarLander-v2 trained agent
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
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
30 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
replay.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: 272.33 +/- 17.74
|
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:": "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 0x7f41b1749dd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f41b1749e60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f41b1749ef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f41b1749f80>", "_build": "<function ActorCriticPolicy._build at 0x7f41b1751050>", "forward": "<function ActorCriticPolicy.forward at 0x7f41b17510e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f41b1751170>", "_predict": "<function ActorCriticPolicy._predict at 0x7f41b1751200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f41b1751290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f41b1751320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f41b17513b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f41b1798960>"}, "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": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1665327484738352399, "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.14", "Stable-Baselines3": "1.6.1", "PyTorch": "1.12.1+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 sha256:3666e99818c58ed834aaf8d7579589fd98309bcae1337f7eeae420eefa24e2bd
|
3 |
+
size 147072
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.1
|
ppo-LunarLander-v2/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 0x7f41b1749dd0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f41b1749e60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f41b1749ef0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f41b1749f80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f41b1751050>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f41b17510e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f41b1751170>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f41b1751200>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f41b1751290>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f41b1751320>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f41b17513b0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f41b1798960>"
|
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": 16,
|
45 |
+
"num_timesteps": 2015232,
|
46 |
+
"_total_timesteps": 2000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1665327484738352399,
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.007616000000000067,
|
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": 492,
|
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 sha256:5bf1e8074d80e069c5c5595111d536086e62eab07cfa397a4d4469c24f291725
|
3 |
+
size 87865
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7174b7b28f9be56a2d724ee9df5700fcab50841ef609361b04ed78bb334a4f53
|
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-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.7.14
|
3 |
+
Stable-Baselines3: 1.6.1
|
4 |
+
PyTorch: 1.12.1+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:b57ff50a07454a15875518b705f9320df7c4475981c1cfca638a58e6dc6452d5
|
3 |
+
size 192597
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 272.3327346759925, "std_reward": 17.743687098613933, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-09T15:52:37.473211"}
|