A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
Published in ICML, 2025
Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL agent’s sample efficiency and generalizability.
Recommended citation: Kang Z, Hu C, Luo Y, et al. A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control[C]//Forty-second International Conference on Machine Learning.
Download Paper