Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

02/01/2023

∙

This paper introduces the Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO) algorithm into reinforcement learning. The Hamilton-Jacobi-Bellman (HJB) equation is used in control theory to evaluate the optimality of the value function. Our work combines the HJB equation with reinforcement learning in continuous state and action spaces to improve the training of the value network. We treat the value network as a Physics-Informed Neural Network (PINN) to solve for the HJB equation by computing its derivatives with respect to its inputs exactly. The Proximal Policy Optimization (PPO)-Clipped algorithm is improvised with this implementation as it uses a value network to compute the objective function for its policy network. The HJBPPO algorithm shows an improved performance compared to PPO on the MuJoCo environments.

READ FULL TEXT

Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

Proximal Deterministic Policy Gradient

Deep Q-Network with Proximal Iteration

Smoothed Action Value Functions for Learning Gaussian Policies

Proximal Learning With Opponent-Learning Awareness

Task-Oriented Cross-System Design for Timely and Accurate Modeling in the Metaverse

Smoothed Dual Embedding Control

Is Epicurus the father of Reinforcement Learning?

Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

Related Research

Proximal Deterministic Policy Gradient

Deep Q-Network with Proximal Iteration

Smoothed Action Value Functions for Learning Gaussian Policies

Proximal Learning With Opponent-Learning Awareness

Task-Oriented Cross-System Design for Timely and Accurate Modeling in the Metaverse

Smoothed Dual Embedding Control

Is Epicurus the father of Reinforcement Learning?