Evolutionary Reinforcement Learning Of Dynamical Large Deviations

Abstract

We show how to calculate the likelihood of dynamical large deviations using evolutionary reinforcement learning. An agent, a stochastic model, propagates a continuous-time Monte Carlo trajectory and receives a reward conditioned upon the values of certain path-extensive quantities. Evolution produces progressively fitter agents, eventually allowing the calculation of a piece of a large-deviation rate function for a particular model and path-extensive quantity. For models with small state spaces the evolutionary process acts directly on rates, and for models with large state spaces the process acts on the weights of a neural network that parameterizes the model's rates. This approach shows how path-extensive physics problems can be considered within a framework widely used in machine learning.

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keywhitelam2019evolutionary

Related papers

• Entropy Regularized Reinforcement Learning Using Large Deviation Theory (2021)6.34
• Distributionally Robust Model-based Reinforcement Learning With Large State Spaces (2023)0.00
• Robust Reinforcement Learning Under Diffusion Models For Data With Jumps (2024)0.00
• Efficient Exploration In Continuous-time Model-based Reinforcement Learning (2023)0.00
• Sample Complexity Of Estimating The Policy Gradient For Nearly Deterministic Dynamical Systems (2019)0.00
• Model-based Reinforcement Learning For Control Under Time-varying Dynamics (2026)0.00
• Dynamic Mean Field Programming (2022)0.00
• Distributional Hamilton-jacobi-bellman Equations For Continuous-time Reinforcement Learning (2022)0.00