Bayesian Nonparametrics for Offline Skill Discovery. (arXiv:2202.04675v3 [cs.LG] UPDATED)

Skills or low-level policies in reinforcement learning are temporally
extended actions that can speed up learning and enable complex behaviours.
Recent work in offline reinforcement learning and imitation learning has
proposed several techniques for skill discovery from a set of expert
trajectories. While these methods are promising, the number K of skills to
discover is always a fixed hyperparameter, which requires either prior
knowledge about the environment or an additional parameter search to tune it.
We first propose a method …

arxiv bayesian discovery lg