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: 284.45 +/- 12.33
|
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 0x7f2750b6a0e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2750b6a170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2750b6a200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2750b6a290>", "_build": "<function ActorCriticPolicy._build at 0x7f2750b6a320>", "forward": "<function ActorCriticPolicy.forward at 0x7f2750b6a3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2750b6a440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2750b6a4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2750b6a560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2750b6a5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2750b6a680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2750baac00>"}, "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": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651857737.610918, "learning_rate": 0.0003, "tensorboard_log": "./ppo_lunarlander_v2", "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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 sha256:33078ce7ecf2726fa3df6e862dd88c7746f42691c321e2bae0a2c11cd56eb3d8
|
3 |
+
size 144019
|
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 0x7f2750b6a0e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2750b6a170>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2750b6a200>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2750b6a290>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f2750b6a320>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f2750b6a3b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2750b6a440>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f2750b6a4d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2750b6a560>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2750b6a5f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2750b6a680>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2750baac00>"
|
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": 2015232,
|
46 |
+
"_total_timesteps": 2000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651857737.610918,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": "./ppo_lunarlander_v2",
|
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": -0.007616000000000067,
|
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": 492,
|
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:eb6574c15bc5c7befcbda5d709330ff3389039b20b1109266f41256dec23a582
|
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:f1f53ff36156a7417d9f3d1ac5aa9ca92a8b52261755ba7facbd82d224c06f9e
|
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 sha256:313b7b0734b91c61857291293fb5ca940b7bd58d2b5156f1759f27d8190cf956
|
3 |
+
size 194029
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 284.4519845821659, "std_reward": 12.331210455883973, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T17:59:48.927508"}
|