ロボット方策学習における密・疎（視覚）報酬の研究
A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning
視覚観測からタスク成功を推定する報酬（密・疎、視覚版含む）を用い、複数の深層強化学習アルゴリズムの性能をシミュレーションタスクで比較した研究。
著者: Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl
分類: cs.RO, cs.LG
原文アブストラクト
Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users. To address such automation, we consider task success classifiers using visual observations to estimate the rewards in terms of task success. In this work, we study the performance of multiple state-of-the-art deep reinforcement learning algorithms under different types of reward: Dense, Sparse, Visual Dense, and Visual Sparse rewards. Our experiments in various simulation tasks (Pendulum, Reacher, Pusher, and Fetch Reach) show that while DRL agents can learn successful behaviours using visual rewards when the goal targets are distinguishable, their performance may decrease if the task goal is not clearly visible. Our results also show that visual dense rewards are more successful than visual sparse rewards and that there is no single best algorithm for all tasks.
