NeurIPS 2024 - Posters and Hallways 1
TalkRL: The Reinforcement Learning Podcast
00:00
Exploring Reinforcement Learning with Hidden Rewards
This chapter delves into exploration strategies within the context of Monitored Markov Decision Processes (MDPs), particularly when rewards are not fully visible. It critiques traditional optimism-based methods and discusses alternative approaches for effectively navigating less observable environments in reinforcement learning applications.
Transcript
Play full episode
