Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability

Understand

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world.

• Designing RL algorithms that optimize these objectives can be a costly and painstaking process.
• This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
• MetaPG explicitly optimizes for generalizability and performance, and implicitly optimizes the stability of both metrics.