Upload PPO LunarLander-v2 trained agent with 10M steps
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-LunarLander-v2_10M.zip +3 -0
- ppo-LunarLander-v2_10M/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2_10M/data +91 -0
- ppo-LunarLander-v2_10M/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2_10M/policy.pth +3 -0
- ppo-LunarLander-v2_10M/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2_10M/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: 270.83 +/- 38.41
|
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 0x7f96e53c5b00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96e53c5b90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f96e53c5c20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96e53c5cb0>", "_build": "<function ActorCriticPolicy._build at 0x7f96e53c5d40>", "forward": "<function ActorCriticPolicy.forward at 0x7f96e53c5dd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f96e53c5e60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f96e53c5ef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f96e53c5f80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96e53cb050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f96e53cb0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f96e5415660>"}, "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": 64, "num_timesteps": 10027008, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651875404.7089593, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3060, "n_steps": 1024, "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": 20, "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_10M.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4306f1156131bb116d08246575014dc57ec0c07e20aa54b38651682337311f96
|
3 |
+
size 143127
|
ppo-LunarLander-v2_10M/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2_10M/data
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f96e53c5b00>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f96e53c5b90>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f96e53c5c20>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f96e53c5cb0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f96e53c5d40>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f96e53c5dd0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f96e53c5e60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f96e53c5ef0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f96e53c5f80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f96e53cb050>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f96e53cb0e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f96e5415660>"
|
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": 64,
|
45 |
+
"num_timesteps": 10027008,
|
46 |
+
"_total_timesteps": 10000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651875404.7089593,
|
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": null,
|
58 |
+
"_last_episode_starts": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_original_obs": null,
|
63 |
+
"_episode_num": 0,
|
64 |
+
"use_sde": false,
|
65 |
+
"sde_sample_freq": -1,
|
66 |
+
"_current_progress_remaining": -0.0027007999999999477,
|
67 |
+
"ep_info_buffer": {
|
68 |
+
":type:": "<class 'collections.deque'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"ep_success_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
74 |
+
},
|
75 |
+
"_n_updates": 3060,
|
76 |
+
"n_steps": 1024,
|
77 |
+
"gamma": 0.99,
|
78 |
+
"gae_lambda": 0.98,
|
79 |
+
"ent_coef": 0.01,
|
80 |
+
"vf_coef": 0.5,
|
81 |
+
"max_grad_norm": 0.5,
|
82 |
+
"batch_size": 64,
|
83 |
+
"n_epochs": 20,
|
84 |
+
"clip_range": {
|
85 |
+
":type:": "<class 'function'>",
|
86 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxYL2hvbWUvdGFnaXIvLmNvbmRhL2VudnMvcmwvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMWC9ob21lL3RhZ2lyLy5jb25kYS9lbnZzL3JsL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flGgOjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
87 |
+
},
|
88 |
+
"clip_range_vf": null,
|
89 |
+
"normalize_advantage": true,
|
90 |
+
"target_kl": null
|
91 |
+
}
|
ppo-LunarLander-v2_10M/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fa268840615aa398b2ec83c159989a2621c48da24982e1143020c060efe3f30
|
3 |
+
size 84893
|
ppo-LunarLander-v2_10M/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e81d01730bd65af022b62d9a3791e3169208df8b21813c56ab37ff3ca1d18982
|
3 |
+
size 43201
|
ppo-LunarLander-v2_10M/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_10M/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 sha256:61883b503642fd8bc7027bc43dfdad99aed45feb6fbf1bd89f50a433e2623271
|
3 |
+
size 211867
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 270.832837985844, "std_reward": 38.4112132462888, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T09:03:33.127724"}
|