Policy Optimization By Genetic Distillation

Abstract

Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly due to the catastrophic consequence of parameter crossovers of neural networks. Here, we present Genetic Policy Optimization (GPO), a new genetic algorithm for sample-efficient deep policy optimization. GPO uses imitation learning for policy crossover in the state space and applies policy gradient methods for mutation. Our experiments on MuJoCo tasks show that GPO as a genetic algorithm is able to provide superior performance over the state-of-the-art policy gradient methods and achieves comparable or higher sample efficiency.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygangwani2017policy

Related papers

• Proximal Policy Optimization Algorithms (2017)0.00
• DGPO: Discovering Multiple Strategies With Diversity-guided Policy Optimization (2022)2.26
• Multi-path Policy Optimization (2019)0.00
• Revisiting Design Choices In Proximal Policy Optimization (2020)0.00
• Hybrid Group Relative Policy Optimization: A Multi-sample Approach To Enhancing Policy Optimization (2025)0.00
• Cautiously Optimistic Policy Optimization And Exploration With Linear Function Approximation (2021)0.00
• Synergizing Reinforcement Learning And Genetic Algorithms For Neural Combinatorial Optimization (2025)0.00
• Policy Optimization With Model-based Explorations (2018)5.84