Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes. (arXiv:2201.11206v1 [cs.LG])

Reward-free reinforcement learning (RL) considers the setting where the agent
does not have access to a reward function during exploration, but must propose
a near-optimal policy for an arbitrary reward function revealed only after
exploring. In the the tabular setting, it is well known that this is a more
difficult problem than PAC RL -- where the agent has access to the reward
function during exploration -- with optimal sample complexities in the two
settings differing by a factor of …

arxiv decision markov processes rl