What Deep Reinforcement Learning Tells Us About Human Motor Learning And Vice-versa

Abstract

Machine learning and specifically reinforcement learning (RL) has been extremely successful in helping us to understand neural decision making processes. However, RL's role in understanding other neural processes especially motor learning is much less well explored. To explore this connection, we investigated how recent deep RL methods correspond to the dominant motor learning framework in neuroscience, error-based learning. Error-based learning can be probed using a mirror reversal adaptation paradigm, where it produces distinctive qualitative predictions that are observed in humans. We therefore tested three major families of modern deep RL algorithm on a mirror reversal perturbation. Surprisingly, all of the algorithms failed to mimic human behaviour and indeed displayed qualitatively different behaviour from that predicted by error-based learning. To fill this gap, we introduce a novel deep RL algorithm: model-based deterministic policy gradients (MB-DPG). MB-DPG draws inspiration

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygaribbo2022what

Related papers

• Machine Versus Human Attention In Deep Reinforcement Learning Tasks (2020)0.00
• Mirror Learning: A Unifying Framework Of Policy Optimisation (2022)0.00
• On The Mistaken Assumption Of Interchangeable Deep Reinforcement Learning Implementations (2025)0.00
• On The Reliability And Generalizability Of Brain-inspired Reinforcement Learning Algorithms (2020)0.00
• Comparing Reinforcement Learning And Human Learning Using The Game Of Hidden Rules (2023)2.26
• An Introduction To Reinforcement Learning For Neuroscience (2023)5.84
• Human-in-the-loop Methods For Data-driven And Reinforcement Learning Systems (2020)0.00
• Modern Deep Reinforcement Learning Algorithms (2019)0.00