rl-baselines3-zoo
rl-baselines3-zoo copied to clipboard
DLR-RM
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Normalization stats should not be updated during evaluation, e.g. in callbacks such as `EvalCallback`. If they are updated during evaluation, it can lead to unexpected inconsistencies between results produced in...
**Describe the bug** I don't know if this was intentional, but I do not expect normalization stats to be updated in an evaluation environment (either in an EvalCallback or in...
If you have any questions, feel free to create an issue with the tag [question]. If you wish to suggest an enhancement or feature request, add the tag [feature request]....
Hi, I was trying to use zoo for tuning my PPO hyperparams, I can't get my vec env to work with zoo. Because I use an environment with multiple agents...
Hi, I'm trying to use rl-baselines3-zoo to train an agent in one of my custom environment, but I'm having trouble registering my env. The readme says : 1. edit utils/import_envs.py...
Hi, I'm using train.py in order to train a second time an agent previous trained to play space invaders. I'm trying to retrain 10M timesteps more, however I can't cause...
## Description Provided the possibility of uploading training args directly from a custom yaml file. E.g. `python train.py --yaml-file custom_training_args.yml`. Note: If other arguments are specified via cli they will...
I was training on custom environment and some trials failed in the middle of the study. I notice optuna offers RetryFailedTrialCallback [https://optuna.readthedocs.io/en/latest/reference/generated/optuna.storages.RetryFailedTrialCallback.html](https://optuna.readthedocs.io/en/latest/reference/generated/optuna.storages.RetryFailedTrialCallback.html). would like to suggest adding this to the...
## Description This is a **draft**, I suggest we keep the conversation in the associated issue: https://github.com/DLR-RM/stable-baselines3/issues/836 ## Motivation and Context - [X] I have raised an issue to propose...
## Description ## Motivation and Context - [ ] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and bug fixes) ## Types of changes -...
