Andreas Doering
commited on
Commit
•
245f3e0
1
Parent(s):
769b08b
Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 118.52 +/- 102.94
|
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**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f7e79386830>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e793868c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e79386950>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e793869e0>", "_build": "<function ActorCriticPolicy._build at 0x7f7e79386a70>", "forward": "<function ActorCriticPolicy.forward at 0x7f7e79386b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e79386b90>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7e79386c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e79386cb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e79386d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e79386dd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7e7935f270>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu", "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////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": 1656704179.5724967, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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": 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:a30342f2d31a55cbe97e604acadaeb665bb3dea6f5cfa133567563817e0de57d
|
3 |
+
size 144143
|
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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f7e79386830>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e793868c0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e79386950>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e793869e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f7e79386a70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f7e79386b00>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e79386b90>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f7e79386c20>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e79386cb0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e79386d40>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e79386dd0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f7e7935f270>"
|
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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////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": 1656704179.5724967,
|
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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
79 |
+
"n_steps": 1024,
|
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:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+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 sha256:0a049525e6486fe34d636e569cd1652305801ee8f8c3d8827aba0c658a54cecb
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:599755fb5d06bd6420925dbab26e5c6e095fe0c57383051ab29475f60b4143ce
|
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:c1059b3e0d3dc3fd6e5e8511f201758374b5ce0910137b817117455a49fb2b05
|
3 |
+
size 240182
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 118.51724781331305, "std_reward": 102.94383702094275, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-01T19:56:38.486246"}
|