joefarrington
commited on
Commit
•
f57d035
1
Parent(s):
0347ddc
Initial commit, using SB3 PPO defaults and trained for 1M timesteps
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- sb3-ppo-LunarLander-v2.zip +3 -0
- sb3-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- sb3-ppo-LunarLander-v2/data +94 -0
- sb3-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- sb3-ppo-LunarLander-v2/policy.pth +3 -0
- sb3-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- sb3-ppo-LunarLander-v2/system_info.txt +7 -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: 272.58 +/- 19.42
|
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 0x7f4a829fac20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4a829facb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4a829fad40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4a829fadd0>", "_build": "<function ActorCriticPolicy._build at 0x7f4a829fae60>", "forward": "<function ActorCriticPolicy.forward at 0x7f4a829faef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4a829faf80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4a82a02050>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4a82a020e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4a82a02170>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4a82a02200>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4a82a40c60>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651785264.5093782, "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": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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"}}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77453745f7123ef969a89b820de74f328ef7f0246b552584487d188b72c8fb59
|
3 |
+
size 209625
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 272.5786489837873, "std_reward": 19.415906403506657, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T21:39:57.380871"}
|
sb3-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:399f9f2ca1191dfadd7d64fac922b4cfaba40c1b5bd1734e536fef2dc188f3d6
|
3 |
+
size 144001
|
sb3-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
sb3-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 0x7f4a829fac20>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4a829facb0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4a829fad40>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4a829fadd0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4a829fae60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4a829faef0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4a829faf80>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4a82a02050>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4a82a020e0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4a82a02170>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4a82a02200>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f4a82a40c60>"
|
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": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651785264.5093782,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+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:": "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": 310,
|
79 |
+
"n_steps": 2048,
|
80 |
+
"gamma": 0.99,
|
81 |
+
"gae_lambda": 0.95,
|
82 |
+
"ent_coef": 0.0,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 10,
|
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 |
+
}
|
sb3-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8565a57177645d9bcdb59fd8b33415d71d5b27d607b0318673270b7ba26318ae
|
3 |
+
size 84893
|
sb3-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9efa0d4f9e53b497ea1e96bc7a05cf30258fdd10f5933b7f436d47416a4514d7
|
3 |
+
size 43201
|
sb3-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
|
sb3-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
|