スコアからの適応学習による対話型強化学習のフィードバック効率向上
Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores
人間が与えるペア比較ではなくスコアを活用し、不完全なスコアにも適応する学習方式で、少ないフィードバックでロボットの移動・操作タスクを効率的に学習する手法を提案した。
著者: Shukai Liu, Chenming Wu, Ying Li, Liangjun Zhang
分類: cs.RO, cs.LG
原文アブストラクト
Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses scores provided by humans instead of pairwise preferences to improve the feedback efficiency of interactive reinforcement learning. Our key insight is that scores can yield significantly more data than pairwise preferences. Specifically, we require a teacher to interactively score the full trajectories of an agent to train a behavioral policy in a sparse reward environment. To avoid unstable scores given by humans negatively impacting the training process, we propose an adaptive learning scheme. This enables the learning paradigm to be insensitive to imperfect or unreliable scores. We extensively evaluate our method for robotic locomotion and manipulation tasks. The results show that the proposed method can efficiently learn near-optimal policies by adaptive learning from scores while requiring less feedback compared to pairwise preference learning methods. The source codes are publicly available at https://github.com/SSKKai/Interactive-Scoring-IRL.
