araffin rl-baselines-zoo issues

araffin / rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

https://stable-baselines.readthedocs.io/

MIT License

1.13k stars 208 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

TypeError: __init__() got an unexpected keyword argument 'timestep_limit'

#122 shangjiayong closed 2 years ago
0
I am getting ImportError in atari environment

#121 ASHISHYADAVSHRI closed 2 years ago
0
Reproducible zoo result

#120 blurLake closed 2 years ago
3
Missing (or can't find) Hyperparameters

#119 jeff-hykin closed 2 years ago
2
[feature request]Add Mujoco-Gym since mujoco is free now

#118 im-Kitsch closed 3 years ago
2
[question] Transfer hyperparameters from optuna

#117 IlonaAT closed 3 years ago
2
SB3 v1.1 Breaking changes

#116 jkterry1 closed 3 years ago
1
Hyperparameter tuning using Custom env with RL-zoo and SB2

#115 shivam-saurav closed 3 years ago
3
[feature request] Hyperparameter optimization for pretrained agent

#114 Jonathan2021 closed 3 years ago
0
[Question] Why is ortho_init=False during hyperparameter searches?

#113 jkterry1 closed 3 years ago
2
[Question] Why do envs look different?

#112 sash-a closed 3 years ago
3
Why during the evaluation VecNormalize stats arenot loaded from the current training stats?

#111 kartikpaigwar closed 3 years ago
1
Can we use it with Tenserflow 2.3.1 ?

#110 deepakraina99 closed 3 years ago
5
BadZipFile when running PPO2.

#109 lubosz closed 4 years ago
5
Irreproducible zoo trials

#108 blurLake closed 4 years ago
5
[feature request] Install Zoo as a package

#107 brendenpetersen closed 4 years ago
6
Multithreaded training with SubprocVecEnv() not working

#106 Simon-Steinmann closed 3 years ago
11
update the baseline for new envs? [feature request]

#105 MartinaRuocco closed 4 years ago
1
How is the trial value calculated for RL jobs?

#104 blurLake closed 4 years ago
1
What is the best initial values for the parameters in the .yml? [question]

#103 toksis closed 4 years ago
4
HER success_rate output [question]

#102 nndei closed 4 years ago
0
Question on optuna terminology

#101 blurLake closed 4 years ago
1
ERROR while using train.py with custom environment

#100 meric-sakarya closed 4 years ago
4
ConnectionResetError: [Errno 104] Connection reset by peer

#99 RayestGeeta closed 4 years ago
0
Fix for new optuna version

#98 araffin closed 4 years ago
0
Hyperparameter tuning fails with Optuna 2.0.0

#97 jatkinson-CRL closed 4 years ago
2
Using custom wrappers while training models

#96 meric-sakarya closed 3 years ago
1
Using the monitor wrapper with ppo2

#95 meric-sakarya closed 4 years ago
3
Changing hyper-parameters in PPO2

#94 meric-sakarya closed 4 years ago
8
SAC Agent For Ant (PyBulletEnv-v0) Has Dimension Mismatch (Training with GAIL)

#93 zrobertson466920 opened 4 years ago
4
[question] Tuning for GAIL and custom envs with time bottlenecks

#92 prabhasak opened 4 years ago
0
[question] In train.py, why is gamma in VecNormalize not updated per trial?

#91 liyan2015 opened 4 years ago
1
Environment reset twice per episode in enjoy script

#90 caburu closed 3 years ago
4
[question] How to Use --env-kwargs correctly?

#89 toksis closed 4 years ago
12
Bug fixes (reward norm in hyperparameter tuning and frame stack for eval env)

#88 araffin closed 4 years ago
0
Use of normalization seems to be weird with hyperparameter tuning

#87 caburu closed 4 years ago
2
Simple spelling correction: 'lamdba' => 'lambda'

#86 josiahcoad closed 4 years ago
0
Bug fixes (HER, lint)

#85 araffin closed 4 years ago
0
Wrapping eval_env with HERGoalEnvWrapper when necessary

#84 PierreExeter closed 4 years ago
1
Why is PPO training slower on VM with GPU

#83 kncrane closed 4 years ago
3
Fix DDPG load error if mpi is not installed.

#82 JohannesUl closed 4 years ago
1
import DDPG failed

#81 JohannesUl closed 4 years ago
1
How to load a pretrained model with hyperparams into a python variable? [Question]

#80 philippwulff closed 4 years ago
2
[Question] When should TimeFeatureWrapper be used?

#79 PierreExeter closed 4 years ago
6
Can't tune hyperparameters with CustomSACPolicy - multiple values for keyword argument 'layers'

#78 PierreExeter closed 4 years ago
5
HER+SAC on Robotic Environment

#77 peiseng closed 4 years ago
5
[question] Why is the environment instantiated differently for DDPG and DQN?

#76 PierreExeter closed 4 years ago
8
Fix StoreDict parsing

#75 araffin closed 4 years ago
0
Retrieving Q-values of trained agents. (Question)

#74 yotamitai closed 4 years ago
3
Optional keyword argument to pass to the env constructor. Solve #58

#73 caburu closed 4 years ago
0