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
@@ -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: 270.09 +/- 20.88
|
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 0x7fd05638fb90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd05638fc20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd05638fcb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd05638fd40>", "_build": "<function ActorCriticPolicy._build at 0x7fd05638fdd0>", "forward": "<function ActorCriticPolicy.forward at 0x7fd05638fe60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd05638fef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd05638ff80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd056396050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd0563960e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd056396170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd0563cfe10>"}, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653048906.644574, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.99, "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:f362d1b68fcab44f0d2b4b9956afd3052e14db5293397f98c623d18cfb930833
|
3 |
+
size 144161
|
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 0x7fd05638fb90>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd05638fc20>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd05638fcb0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd05638fd40>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd05638fdd0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd05638fe60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd05638fef0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd05638ff80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd056396050>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd0563960e0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd056396170>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fd0563cfe10>"
|
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": 1507328,
|
46 |
+
"_total_timesteps": 1500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653048906.644574,
|
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": -0.004885333333333408,
|
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": 368,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.99,
|
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:b3d128b97c924c8b28729b6e59c10c150b82a9c53381725df239ff10d922d78d
|
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:e26ebc9c3947a605d08eccf8b55c359a378f5fbef684c8b75185bbca6f4991e5
|
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 sha256:4574e24f023fb081366e0b5d93f266ee1835949e5e134ac42e90688960b83dde
|
3 |
+
size 193168
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 270.08886650303305, "std_reward": 20.882859062065723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T12:58:34.612335"}
|