2020/03/29 by Sergey Kolesnikov, Kolesnikov, Sergey, Valentin Khrulkov +1
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Neural Networks and Applications #Reinforcement Learning in Robotics #cs.AI #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2003.14210
arXiv admin note: substantial text overlap with arXiv:1903.00027
openalex publication_date 2020/03/29 · arxiv created 2020/04/07 · arxiv updated 2020/04/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scale asynchronous distributed training, efficient implementations of various RL algorithms and auxiliary tricks, such as n-step returns, value distributions, hyperbolic reinforcement learning, etc. To demonstrate the effectiveness of Catalyst.RL, we applied it to a physics-based reinforcement learning challenge "NeurIPS 2019: Learn to Move -- Walk Around" with the objective to build a locomotion controller for a human musculoskeletal model. The environment is computationally expensive, has a high-dimensional continuous action space and is stochastic. Our team took the 2nd place, capitalizing on the ability of Catalyst.RL to train high-quality and sample-efficient RL agents in only a few hours of training time. The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out.