Hindsight Trust Region Policy Optimization [article]

Hanbo Zhang, Site Bai, Xuguang Lan, David Hsu, Nanning Zheng
2021 arXiv   pre-print
Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose Hindsight Trust Region Policy Optimization(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with hindsight to tackle the challenge of sparse rewards. Hindsight refers to the algorithm's ability to learn from information across goals, including ones not intended for the current task. HTRPO leverages two main ideas. It introduces QKL, a quadratic approximation to the KL divergence
more » ... on the trust region, leading to reduced variance in KL divergence estimation and improved stability in policy update. It also presents Hindsight Goal Filtering(HGF) to select conductive hindsight goals. In experiments, we evaluate HTRPO in various sparse reward tasks, including simple benchmarks, image-based Atari games, and simulated robot control. Ablation studies indicate that QKL and HGF contribute greatly to learning stability and high performance. Comparison results show that in all tasks, HTRPO consistently outperforms both TRPO and HPG, a state-of-the-art algorithm for RL with sparse rewards.
arXiv:1907.12439v5 fatcat:px2ffrbvjrafhe6obr2mkudgym