Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach
NeurIPSSpotlight2025
TL;DR
Traditional reinforcement learning (RL) assumes the agents make decisions based on Markov decision processes (MDPs) with one-step transition models…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
reinforcement learning agent llm
← All NeurIPS 2025 Spotlight papers · Browse the whole archive