Meta-reinforcement Learning With Self-modifying Networks

Abstract

Deep Reinforcement Learning has demonstrated the potential of neural networks tuned with gradient descent for solving complex tasks in well-delimited environments. However, these neural systems are slow learners producing specialized agents with no mechanism to continue learning beyond their training curriculum. On the contrary, biological synaptic plasticity is persistent and manifold, and has been hypothesized to play a key role in executive functions such as working memory and cognitive flexibility, potentially supporting more efficient and generic learning abilities. Inspired by this, we propose to build networks with dynamic weights, able to continually perform self-reflexive modification as a function of their current synaptic state and action-reward feedback, rather than a fixed network configuration. The resulting model, MetODS (for Meta-Optimized Dynamical Synapses) is a broadly applicable meta-reinforcement learning system able to learn efficient and powerful control rules in

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keychalvidal2022meta

Related papers

• Context Meta-reinforcement Learning Via Neuromodulation (2021)6.34
• Lifelong Reinforcement Learning Via Neuromodulation (2024)0.00
• Overcoming Catastrophic Interference In Online Reinforcement Learning With Dynamic Self-organizing Maps (2019)0.00
• Learning To Reinforcement Learn (2016)0.00
• Meta-gradient Reinforcement Learning With An Objective Discovered Online (2020)0.00
• Deep Online Learning Via Meta-learning: Continual Adaptation For Model-based RL (2018)0.00
• Reinforcement Learning With Brain-inspired Modulation Can Improve Adaptation To Environmental Changes (2022)0.00
• Improving Generalization In Meta Reinforcement Learning Using Learned Objectives (2019)0.00