Noah Farr

Implement CrossQ

1

## Problem Description I would like to implement the CrossQ algorithm as proposed in https://openreview.net/pdf?id=PczQtTsTIX. I already did some testing and it looks like its not that much effort to...

WIP: Implement CrossQ for continuous actions

2

## Description Implementing #463 ## Types of changes - [ ] Bug fix - [ ] New feature - [x] New algorithm - [ ] Documentation ## Checklist: - [x]...

Add TD3 and SAC support for multiple envs

1

## Description TD3 and SAC currently doesnt support running multiple environments. Its easy to add by adding a num_envs param and passing it to the env creation and replay buffer...

Add utilities to distributions

3

In pytorch, the following is easily possible: ```python logits = ... probs = Categorical(logits=logits) log_prob = probs.log_prob(value) entropy = probs.entropy() ``` but when I want to achieve something similar in...

Remove DDPG noise clip parameter

1

## Description The noise_clip parameter is not used in DDPG so we can remove it. ## Types of changes - [x] Bug fix - [ ] New feature - [...