Upload PPO LunarLander-v2 trained agent
Browse files- ModelPPO1.zip +3 -0
- ModelPPO1/_stable_baselines3_version +1 -0
- ModelPPO1/data +99 -0
- ModelPPO1/policy.optimizer.pth +3 -0
- ModelPPO1/policy.pth +3 -0
- ModelPPO1/pytorch_variables.pth +3 -0
- ModelPPO1/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
ModelPPO1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c925c5046e93cb9c8fe3b0e5642b094c490d2c2fec52bb3c5d06d95a9667b0a3
|
3 |
+
size 147899
|
ModelPPO1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ModelPPO1/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x79f87db37520>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f87db375b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f87db37640>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f87db376d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x79f87db37760>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x79f87db377f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x79f87db37880>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f87db37910>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x79f87db379a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f87db37a30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f87db37ac0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x79f87db37b50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x79f87daded40>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 16384,
|
25 |
+
"_total_timesteps": 1000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1699008455511923035,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -15.384,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 4,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.9,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
ModelPPO1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d90eb05e1845dd091915fc9318b5854feadbfb0dd5da9b092770c04dd4924b77
|
3 |
+
size 88362
|
ModelPPO1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60ea8c6d8cbbce6faf20cb284c9a2616cd0424beaed9ce70d57211aeecb4ec8d
|
3 |
+
size 43762
|
ModelPPO1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ModelPPO1/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
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: -795.59 +/- 312.71
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x79f87db37520>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79f87db375b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79f87db37640>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79f87db376d0>", "_build": "<function ActorCriticPolicy._build at 0x79f87db37760>", "forward": "<function ActorCriticPolicy.forward at 0x79f87db377f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79f87db37880>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79f87db37910>", "_predict": "<function ActorCriticPolicy._predict at 0x79f87db379a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79f87db37a30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79f87db37ac0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79f87db37b50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79f87daded40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1699008455511923035, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -15.384, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.9, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (68.6 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -795.5940112, "std_reward": 312.710695231623, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-03T11:32:03.775205"}
|