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 +/- 19.04
|
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 0x7f62a4060560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f62a40605f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f62a4060680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f62a4060710>", "_build": "<function ActorCriticPolicy._build at 0x7f62a40607a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f62a4060830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f62a40608c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f62a4060950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f62a40609e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f62a4060a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f62a4060b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f62a40ad7b0>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1654762974.013525, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 372, "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-5.4.188+-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 sha256:3540f5c4d973f83cff7826ced26c87061a67d369b70ac0f9263eaa4ab9ec6259
|
3 |
+
size 144213
|
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 0x7f62a4060560>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f62a40605f0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f62a4060680>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f62a4060710>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f62a40607a0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f62a4060830>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f62a40608c0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f62a4060950>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f62a40609e0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f62a4060a70>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f62a4060b00>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f62a40ad7b0>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1654762974.013525,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
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": -0.015808000000000044,
|
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": 372,
|
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 sha256:664eaeb1fa953e2dd3f9f0c9e7325fe2c6cfaf4227e3b357aa03d60327797013
|
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:f2a9684fa9357715ce4fcf587e0d051897c300b5b9d501343f362372000a223f
|
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 sha256:39f7feb45eb73c0e02c1d36438fc3039ab91a71079dc52a9986f6896dfca115c
|
3 |
+
size 197642
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 270.09393344333625, "std_reward": 19.037368884800358, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-09T09:01:11.569084"}
|