Raiden-1001
commited on
Commit
•
cbdd6b9
1
Parent(s):
82edfe3
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -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 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: -150.87 +/- 42.66
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
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 0x7fbf3e380790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbf3e380820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbf3e3808b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbf3e380940>", "_build": "<function ActorCriticPolicy._build at 0x7fbf3e3809d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fbf3e380a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbf3e380af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbf3e380b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbf3e380c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbf3e380ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbf3e380d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbf3e3810c0>"}, "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": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670953330075257728, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 32, "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-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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:bb4cad6d13c9dbe4e791303d4c1a51502e382666c39d771ec979c243d8f313e5
|
3 |
+
size 147081
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
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 0x7fbf3e380790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbf3e380820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbf3e3808b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbf3e380940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fbf3e3809d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fbf3e380a60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbf3e380af0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fbf3e380b80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbf3e380c10>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbf3e380ca0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbf3e380d30>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fbf3e3810c0>"
|
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": 114688,
|
46 |
+
"_total_timesteps": 100000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1670953330075257728,
|
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:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJoBU72wj/E+Fe/TPcVsXr/QL269IItjPQAAAAAAAAAAiMKvvvTCsj9mvgi/sjwsvgI9nr4F/KK+AAAAAAAAAABis4y+gpViP8o1vL4p7SC/IbSzvlu11r0AAAAAAAAAAIB0LT7c4ko9jtikPvwEeb8bQRg9qneJPgAAAAAAAAAAAMXyPCcysT8+i849Dkltvne0tb2gDGE9AAAAAAAAAAAm0DU+Y95WP8m+hj40Mz+/xetjPYuHGb0AAAAAAAAAAPMw0T2V9a4/T1EOP9mwZL4lLVS854ayugAAAAAAAAAA+jZ8vmzemz/msyO/VEL4vnHlEr2ih/K9AAAAAAAAAAAAPK+85wViPwhWqb3E2k2/o6EavV65dr0AAAAAAAAAAADy/Tz4dLE/te3BPk8HV74AFGq8AvjfPAAAAAAAAAAAnfmDPvr2rj5rzfY+eHyEv534jr11l/g9AAAAAAAAAAAAdLA8yXyxP2LO1z6GxYm+9rODvMP3XbwAAAAAAAAAAE2BSz2v7Do+RHayPRmWcb//Xlq8DhsEvgAAAAAAAAAAMuUTPwoQDb6VeQA/a7cVv/C/4rzGD6m/AACAPwAAgD+aea2799G1P/FGCb9JTtk+IzzJO0PD+D0AAAAAAAAAAPOG9b0DoCc/c1Npvib2VL+4vku+9RFZvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": -0.1468799999999999,
|
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": 32,
|
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:b36254b61e1a72dc129ad2c12e62113318fd7b0c094481e661e83d8a50298f7f
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f91611bc5748b44396c22288f3b82df91ca8742944d6ac6721968908b708cd5
|
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-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (273 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -150.87325544391697, "std_reward": 42.65768053096808, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T17:50:40.645172"}
|