Relay Generalization of Reinforcement Learning
- 講者藍立呈 先生 (Computer Science, University of California, Los Angeles)
邀請人：吳廸融 - 時間2022-12-15 (Thu.) 14:00 ~ 16:00
- 地點資訊所舊館108演講廳
摘要
Generalization is critical for deploying reinforcement learning (RL) agents into real-world applications. A well-trained RL agent that can achieve high rewards under restricted settings may not be able to handle the enormous state space and complex environment variations in the real world. We propose, study, and improve the "relay-generalization" — a well-generalized agent that masters a task should be able to start from any “controllable” state in the same environment and still reach the goal. For example, a self-driving system may need to take over the control from humans in the middle of driving and must continue to drive the car safely. We show that the current RL methods are not general enough to pass our "relay-evaluation". We also propose a novel method called Self-Trajectory Augmentation (STA) which can reduce the failure rate dramatically.