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: -56.07 +/- 101.97
|
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 0x7fb5ea85d0d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb5ea85d160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb5ea85d1f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb5ea85d280>", "_build": "<function ActorCriticPolicy._build at 0x7fb5ea85d310>", "forward": "<function ActorCriticPolicy.forward at 0x7fb5ea85d3a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb5ea85d430>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb5ea85d4c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb5ea85d550>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb5ea85d5e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb5ea85d670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb5ea851f60>"}, "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": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651873159.336957, "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": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8, "n_steps": 16384, "gamma": 0.99, "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": "macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 20.6.0: Mon Aug 30 06:12:21 PDT 2021; root:xnu-7195.141.6~3/RELEASE_X86_64", "Python": "3.8.8", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43515c42d7a1b5c6e4f761875adfee11319306635e8bbbc79c5f93bb3fe1c977
|
3 |
+
size 143902
|
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 0x7fb5ea85d0d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb5ea85d160>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb5ea85d1f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb5ea85d280>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb5ea85d310>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb5ea85d3a0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb5ea85d430>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb5ea85d4c0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb5ea85d550>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb5ea85d5e0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb5ea85d670>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fb5ea851f60>"
|
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": 524288,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651873159.336957,
|
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": -0.04857599999999995,
|
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": 8,
|
79 |
+
"n_steps": 16384,
|
80 |
+
"gamma": 0.99,
|
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:a41f57c74fbf8cf8efc41a6f79722444005731f7370843186fee9fb768ab5a44
|
3 |
+
size 84573
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddee3c84eff332e0bc359d88700e0d7d01d108b1d715b7d761bbc3ebea6cf1a0
|
3 |
+
size 43073
|
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: macOS-10.16-x86_64-i386-64bit Darwin Kernel Version 20.6.0: Mon Aug 30 06:12:21 PDT 2021; root:xnu-7195.141.6~3/RELEASE_X86_64
|
2 |
+
Python: 3.8.8
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.22.3
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7518549f67c1146ab5b18bee39a2d8af8c72cc5603f8788a53907f32959fac0e
|
3 |
+
size 342196
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -56.072621469286744, "std_reward": 101.97480365335419, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T00:55:06.844559"}
|