Dueling Posterior Sampling for Preference-Based Reinforcement Learning

1 code implementation • 4 Aug 2019 • Ellen R. Novoseller, Yibing Wei, Yanan Sui, Yisong Yue, Joel W. Burdick

In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback.

reinforcement-learning Reinforcement Learning (RL)