AI RESEARCH
Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
arXiv CS.LG
•
ArXi:2602.01295v3 Announce Type: replace We investigate episodic Marko Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms HT-FTRL-OM and HT-FTRL-UOB for HTMDPs that achieve Best-of-Both-Worlds (BoBW) guarantees: instance-independent regret in adversarial environments and logarithmic instance-dependent regret in self-bounding (including the stochastic case) environments.