適応的リスク選好:混雑環境におけるナノドローンの分布強化学習ナビゲーション
Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning
ナノクアッドコプターが未知の混雑環境を部分観測下で航行するため、リターン分布の下側裾条件付き分散を不確実性推定に用い、指数加重平均予測でリスク選好を適応させる分布強化学習を提案した。
著者: Cheng Liu, Erik-Jan van Kampen, Guido C. H. E. de Croon
分類: cs.RO, cs.AI
原文アブストラクト
Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones. In this paper, we investigate a specific case where a nano quadcopter robot learns to navigate an apriori-unknown cluttered environment under partial observability. We present a distributional reinforcement learning framework to generate adaptive risk-tendency policies. Specifically, we propose to use lower tail conditional variance of the learnt return distribution as intrinsic uncertainty estimation, and use exponentially weighted average forecasting (EWAF) to adapt the risk-tendency in accordance with the estimated uncertainty. In simulation and real-world empirical results, we show that (1) the most effective risk-tendency vary across states, (2) the agent with adaptive risk-tendency achieves superior performance compared to risk-neutral policy or risk-averse policy baselines.
