Abstract
We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with limited interactions per task. The agent can use its experience in each task \emph{and} across tasks to estimate both the transition model and the distribution over tasks. We propose an algorithm to meta-learn the underlying relatedness across tasks, utilize it to plan in each task, and upper-bound the regret of the planning loss. Our bound suggests that the average regret over tasks decreases as the number of tasks increases and as the tasks are more similar. In the classical single-task setting, it is known that the planning horizon should depend on the estimated model's accuracy, that is, on the number of samples within task. We generalize this finding to meta-RL and study this dependence of planning horizon on the number of tasks. Based on our theoretical findings, we derive heuristics for selecting slowly increasing discount factors, and validate its significance empirically.
Authors
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy
Venue
NeurIPS Workshop 2023