D'BEAST: 悪い経験を説明として用いる自動運転エージェントの意思決定分析
D'BEAST: Logged Bad Experiences as Explanation for Autonomous Driving Agents
強化学習エージェントの意思決定が、安全やタスクに関わる「悪い経験」に基づくかを検証し、それらを除去すると失敗することをCARLA運転タスクで示した研究。
著者: Ahmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur Arief
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Reinforcement learning agents learn from mistakes, yet their decisions can be difficult to trace back to those experiences. We investigate whether a tabular agent's decisions can be explained by its bad experiences, defined as the training transitions associated with safety or task events. A fixed training log is replayed from the same initial Q-table under three conditions. FULL retains all updates, SKIP omits bad-experience updates, and NEUTRALIZE retains those updates without their event penalties. We illustrate the method on six classic Markov decision processes and evaluate it in closed-loop driving in CARLA. On the full driving task, FULL reached the goal from 33 of 40 test starts, whereas SKIP and NEUTRALIZE reached it from none, indicating that the bad experiences carry decision-relevant information. At the local level, for 47 decisions shortly before a failure of SKIP or NEUTRALIZE, removing or neutralizing a small group of bad experiences, with a median size of one, caused the trained agent to select the failing policy's action in 46 cases. For this agent, the results indicate that its decisions can be explained by its bad experiences.
