On The Reliability And Generalizability Of Brain-inspired Reinforcement Learning Algorithms

Abstract

Although deep RL models have shown a great potential for solving various types of tasks with minimal supervision, several key challenges remain in terms of learning from limited experience, adapting to environmental changes, and generalizing learning from a single task. Recent evidence in decision neuroscience has shown that the human brain has an innate capacity to resolve these issues, leading to optimism regarding the development of neuroscience-inspired solutions toward sample-efficient, and generalizable RL algorithms. We show that the computational model combining model-based and model-free control, which we term the prefrontal RL, reliably encodes the information of high-level policy that humans learned, and this model can generalize the learned policy to a wide range of tasks. First, we trained the prefrontal RL, and deep RL algorithms on 82 subjects' data, collected while human participants were performing two-stage Markov decision tasks, in which we manipulated the goal, stat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykim2020on

Related papers

• Assessing Generalization In Deep Reinforcement Learning (2018)0.00
• An Introduction To Reinforcement Learning For Neuroscience (2023)5.84
• Efficient Deep Reinforcement Learning With Predictive Processing Proximal Policy Optimization (2022)0.00
• Generalizing Skills With Semi-supervised Reinforcement Learning (2016)0.00
• Learning To Reinforcement Learn (2016)0.00
• Reinforcement Learning With Brain-inspired Modulation Can Improve Adaptation To Environmental Changes (2022)0.00
• Generalized Bayesian Deep Reinforcement Learning (2024)0.00
• Human-inspired Framework To Accelerate Reinforcement Learning (2023)0.00