失敗から学ぶ:エピソディックメモリを用いた効率的な強化学習制御
Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory
強化学習の初期訓練で頻発する衝突や転倒などの失敗経験をエピソディックメモリに保存し、類似失敗を回避して長期的な軌道を探索する手法FEMAを提案。モデルフリーRLに容易に組み込め、MuJoCoタスクでサンプル効率を33.11%向上させ、実ロボットの二足歩行タスクでも有効性を確認した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Chenyang Miao
分類: cs.RO
原文アブストラクト
Reinforcement learning has achieved remarkable success in robot learning. However, under challenging exploration and contact-rich dynamics, early-stage training is frequently dominated by premature terminations such as collisions and falls. As a result, learning is overwhelmed by short-horizon, low-return trajectories, which hinder convergence and limit long-horizon exploration. To alleviate this issue, we propose a technique called Failure Episodic Memory Alert (FEMA). FEMA explicitly stores short-horizon failure experiences through an episodic memory module. During interactions, it retrieves similar failure experiences and prevents the robot from recurrently relapsing into unstable states, guiding the policy toward long-horizon trajectories with greater long-term value. FEMA can be combined easily with model-free reinforcement learning algorithms, and yields a substantial sample-efficiency improvement of 33.11% on MuJoCo tasks across several classical RL algorithms. Furthermore, integrating FEMA into a parallelized PPO training pipeline demonstrates its effectiveness on a real-world bipedal robot task.
