kosta-naumenko
commited on
Commit
•
c2785e0
1
Parent(s):
d531652
Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +28 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 228.05 +/- 22.63
|
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** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
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 0x7f5362af95f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5362af9680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5362af9710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5362af97a0>", "_build": "<function ActorCriticPolicy._build at 0x7f5362af9830>", "forward": "<function ActorCriticPolicy.forward at 0x7f5362af98c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5362af9950>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5362af99e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5362af9a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5362af9b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5362af9b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5362b3ade0>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652212595.3057692, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 140, "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 sha256:3b99de6b68c8b1b35cf7c604ac11f09eb029ca8951d0aed21dcca6cc59068b6d
|
3 |
+
size 144044
|
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:": "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 0x7f5362af95f0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5362af9680>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5362af9710>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5362af97a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5362af9830>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5362af98c0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5362af9950>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5362af99e0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5362af9a70>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5362af9b00>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5362af9b90>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f5362b3ade0>"
|
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": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1652212595.3057692,
|
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": -0.015808000000000044,
|
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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 140,
|
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:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
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 sha256:89b41d15bf7b39bce9c969aa1c022c66f8226f43bc16c5ccc22bba0563964c95
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ea2344a196400de0deca2a2f8d73557caa9781a28438bce341cef84c6913448
|
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 sha256:8054e7a3c6678a842bc4a8dfd44fa96ba935ea5d77503169dce8761b4d4dd217
|
3 |
+
size 230947
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 228.04540874868462, "std_reward": 22.62784815344382, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T20:06:40.601917"}
|