Answers are grounded in this paper and cite their sources.
We explore the generality of Reinforcement Learning (RL) agents on unseen environment configurations by analyzing the behavior of an agent tasked with traversing a graph based environment from a starting position to a goal position. We find that training on a single task is likely to result in inflexible policies that do not respond well to change. Instead, training on a wide variety of scenarios offers the best chance of developing a flexible policy, at the expense of increased training difficulty.
No takes yet. Share an insight, caveat, or question.
Kitchen et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: