A Story Of Two Streams: Reinforcement Learning Models From Human Behavior And Neuropsychiatry

Abstract

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-processing biases -- an important component of human decision making which can help us better understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems, as well as various neuropsychiatric conditions associated with disruptions in normal reward processing. From the computational perspective, we observe that the proposed Split-QL model and its clinically inspired variants consistently outperform standard Q-Learning and SARSA methods, as well as recently proposed Double Q-Learning approaches, on simulated tasks with particular reward distributions, a real-world dataset capturing human decision-making in gambling tasks, and the Pac-Man gam

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylin2019a

Related papers

• Unified Models Of Human Behavioral Agents In Bandits, Contextual Bandits And RL (2020)8.35
• Reinforcement Learning And Its Connections With Neuroscience And Psychology (2020)12.25
• HMM For Discovering Decision-making Dynamics Using Reinforcement Learning Experiments (2024)0.00
• Adaptive Symmetric Reward Noising For Reinforcement Learning (2019)0.00
• Implications Of Human Irrationality For Reinforcement Learning (2020)0.00
• Unified Algorithms For RL With Decision-estimation Coefficients: PAC, Reward-free, Preference-based Learning, And Beyond (2022)5.24
• An Introduction To Reinforcement Learning For Neuroscience (2023)5.84
• Self Punishment And Reward Backfill For Deep Q-learning (2020)7.16