davidcarmel
commited on
Commit
·
966021e
1
Parent(s):
9d874c9
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -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 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 262.96 +/- 21.25
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
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 0x7fb57b02cee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb57b02cf70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb57b030040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb57b0300d0>", "_build": "<function ActorCriticPolicy._build at 0x7fb57b030160>", "forward": "<function ActorCriticPolicy.forward at 0x7fb57b0301f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb57b030280>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb57b030310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb57b0303a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb57b030430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb57b0304c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb57b02a6f0>"}, "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": 1672301107316240647, "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": 248, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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:dd00779eddc74c778d086c5d4ddb4c741f25fcd6de04b7e8bc43bc5fc32d321f
|
3 |
+
size 147210
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
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 0x7fb57b02cee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb57b02cf70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb57b030040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb57b0300d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb57b030160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb57b0301f0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb57b030280>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb57b030310>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb57b0303a0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb57b030430>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb57b0304c0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fb57b02a6f0>"
|
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": 1672301107316240647,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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": 248,
|
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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
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 sha256:70718874423e23aa2cd8d14ea485df62de97e34a621dfb4f5529ae3cfa868c11
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:566044d013120bbcc9d3394d1a0b598a9fd2ebe7b3bb7fa9d2ba9070d3a7849a
|
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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (213 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 262.9615736366742, "std_reward": 21.24950382154135, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T09:09:38.640268"}
|