Humans Are Not Boltzmann Distributions: Challenges And Opportunities For Modelling Human Feedback And Interaction In Reinforcement Learning

Abstract

Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide. Instead, recently, more work has explored learning what to do from interacting with humans. So far, most of these approaches model humans as being (nosily) rational and, in particular, giving unbiased feedback. We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. In particular, we argue that human models have to be personal, contextual, and dynamic. This paper calls for research from different disciplines to address key questions about how humans provide feedback to AIs and how we can build more robust human-in-the-loop RL systems.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylindner2022humans

Related papers

• Mapping Out The Space Of Human Feedback For Reinforcement Learning: A Conceptual Framework (2024)0.00
• When Your Ais Deceive You: Challenges Of Partial Observability In Reinforcement Learning From Human Feedback (2024)0.00
• Perspectives On The Social Impacts Of Reinforcement Learning With Human Feedback (2023)0.00
• A Survey Of Reinforcement Learning From Human Feedback (2023)0.00
• Implications Of Human Irrationality For Reinforcement Learning (2020)0.00
• Provably Feedback-efficient Reinforcement Learning Via Active Reward Learning (2023)0.00
• Improving Multimodal Interactive Agents With Reinforcement Learning From Human Feedback (2022)0.00
• A Survey On Enhancing Reinforcement Learning In Complex Environments: Insights From Human And LLM Feedback (2024)0.00