CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents

Sam Powers, Eliot Xing, Eric Kolve, Roozbeh Mottaghi, Abhinav Gupta

Abstract: Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present ...