Skip to content
conftrace_

trajectory label

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reinforcement learning (2) reward modelling (1) once-per-episode feedback (1) non-markovian reward (1) binary feedback (1) temporal dependency (1) interpretable model (1) sublinear regret (1) parametric model (1) trajectory analysis (1)

Papers

Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning NeurIPS 2022 On the Theory of Reinforcement Learning with Once-per-Episode Feedback NeurIPS 2021