External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling
This work addresses the challenge of multitask adaptation in reinforcement learning for agents operating in dynamic settings, representing an incremental improvement.
The paper tackles the problem of reinforcement learning agents adapting inefficiently in changing environments by proposing an agent influence framework that improves external model adaptation without altering rewards, achieving superior performance and efficiency over baselines.
Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks with learning about how changes may affect their understanding of the world. This is possible by choosing to solve tasks in ways that are interesting and generally informative beyond just the current task. Motivated by this, we propose an agent influence framework for RL agents to improve the adaptation efficiency of external models in changing environments without any changes to the agent's rewards. Our formulation is composed of two self-contained modules: interest fields and behavior shaping via interest fields. We implement an uncertainty-based interest field algorithm as well as a skill-sampling-based behavior-shaping algorithm to use in testing this framework. Our results show that our method outperforms the baselines in terms of external model adaptation on metrics that measure both efficiency and performance.