Measuring and Characterizing Generalization in Deep Reinforcement Learning

Understand

Deep reinforcement-learning methods have achieved remarkable performance on challenging control tasks.

• Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports insightful action decisions.
• We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states.
• We propose a set of practical methods for evaluating agents with these definitions of generalization.