Tuning for the Unknown: Revisiting Evaluation Strategies for Lifelong RL

arXiv:2404.02113v1 Announce Type: new
Abstract: In continual or lifelong reinforcement learning access to the environment should be limited. If we aspire to design algorithms that can run for long-periods of time, continually adapting to new, unexpected situations then we must be willing to deploy our agents without tuning their hyperparameters over the agent's entire lifetime. The standard practice in deep RL -- and even continual RL -- is to assume unfettered access to deployment environment for the full lifetime of …

abstract agents algorithms arxiv aspire continual cs.lg deploy design environment evaluation reinforcement reinforcement learning strategies the environment the unknown type