Surrogate-assisted Evolutionary Reinforcement Learning Based On Autoencoder And Hyperbolic Neural Network
2025 · Bingdong Li, Mei Jiang, Hong Qian, et al.
Abstract
Evolutionary Reinforcement Learning (ERL), training the Reinforcement Learning (RL) policies with Evolutionary Algorithms (EAs), have demonstrated enhanced exploration capabilities and greater robustness than using traditional policy gradient. However, ERL suffers from the high computational costs and low search efficiency, as EAs require evaluating numerous candidate policies with expensive simulations, many of which are ineffective and do not contribute meaningfully to the training. One intuitive way to reduce the ineffective evaluations is to adopt the surrogates. Unfortunately, existing ERL policies are often modeled as deep neural networks (DNNs) and thus naturally represented as high-dimensional vectors containing millions of weights, which makes the building of effective surrogates for ERL policies extremely challenging. This paper proposes a novel surrogate-assisted ERL that integrates Autoencoders (AE) and Hyperbolic Neural Networks (HNN). Specifically, AE compresses high-dime
Authors
(none)
Tags
Stats
Related papers
- Evolution-guided Policy Gradient In Reinforcement Learning (2018)0.00
- Erl-re\(^2\): Efficient Evolutionary Reinforcement Learning With Shared State Representation And Individual Policy Representation (2022)0.00
- An Efficient Asynchronous Method For Integrating Evolutionary And Gradient-based Policy Search (2020)0.00
- Evolutionary Reinforcement Learning Via Cooperative Coevolutionary Negatively Correlated Search (2020)9.92
- Synergizing Reinforcement Learning And Genetic Algorithms For Neural Combinatorial Optimization (2025)0.00
- Collaborative Evolutionary Reinforcement Learning (2019)0.00
- Bridging Evolutionary Algorithms And Reinforcement Learning: A Comprehensive Survey On Hybrid Algorithms (2024)17.05
- Autoeg: Automated Experience Grafting For Off-policy Deep Reinforcement Learning (2020)0.00