Work

DLR-RM/rl-baselines3-zoo: RL Zoo v2.5.0: NumPy v2.0 support

Year: 2023

Type: software

Abstract: Breaking Changes Updated defaults hyperparameters for TD3/DDPG to be more consistent with SAC Upgraded MuJoCo envs hyperparameters to v4 (pre-trained agents need to be updated) Upgraded to SB3 >= 2.3.0 Other Added test dependencies to setup.py (@power-edge) Simplify dependencies of requirements.txt (remove duplicates from setup.py) Full Changelog: https://github.com/DLR-RM/rl-baselines3-zoo/compare/v2.2.1...v2.3.0

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.8266961

Authors: Antonin RAFFIN, Quentin Gallouédec, Jordan Terry, M. Ernestus, Martiño Crespo, Salman Shaikh, Costa Huang, Affonso, Guilherme, Amanda Dsouza, Andreas Schuderer, Ayush Bishnoi, Carl Boettiger, Cyprien, Darío Hereñú, Eric Chen, Grégoire Passault, Guspan Tanadi, JieQiang (Jay) Wei, JohannesUl, Marc Bestmann, Markus Bertheau, Nikhil Rayaprolu, Prasad Chalasani, Rick-v-E, Sang Hyun Son, Scott Emmons, Sean Gillen, Thomas Simonini, Toshiki Watanabe, Vinay Arjun Hajare

Institutions: Hugging Face, University of California, Berkeley, Johns Hopkins University Applied Physics Laboratory, Freelancer (Portugal)

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W6912866454

Cites:

Cited by:

Related to: 10