One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning
Pedro Cisneros-Velarde, Boxiang Lyu, Sanmi Koyejo, Mladen Kolar · arXiv: 2205.15891v3 · Summary page
Your journal club presentation, ready in a minute. About ten slides with the figures of the paper when its license allows it, what to say on each one, the strengths and limits of the paper, and questions to start the discussion. Present it full screen or save it as PDF.