Adaptive Combination Of A Genetic Algorithm And Novelty Search For Deep Neuroevolution

Abstract

Evolutionary Computation (EC) has been shown to be able to quickly train Deep Artificial Neural Networks (DNNs) to solve Reinforcement Learning (RL) problems. While a Genetic Algorithm (GA) is well-suited for exploiting reward functions that are neither deceptive nor sparse, it struggles when the reward function is either of those. To that end, Novelty Search (NS) has been shown to be able to outperform gradient-following optimizers in some cases, while under-performing in others. We propose a new algorithm: Explore-Exploit \(\gamma\)-Adaptive Learner (\(E^2\gamma AL\), or EyAL). By preserving a dynamically-sized niche of novelty-seeking agents, the algorithm manages to maintain population diversity, exploiting the reward signal when possible and exploring otherwise. The algorithm combines both the exploitation power of a GA and the exploration power of NS, while maintaining their simplicity and elegance. Our experiments show that EyAL outperforms NS in most scenarios, while being on p

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysegal2022adaptive

Related papers

• Improving Exploration In Evolution Strategies For Deep Reinforcement Learning Via A Population Of Novelty-seeking Agents (2017)0.00
• Synergizing Reinforcement Learning And Genetic Algorithms For Neural Combinatorial Optimization (2025)0.00
• Evolutionary Reinforcement Learning Via Cooperative Coevolutionary Negatively Correlated Search (2020)9.92
• PNS: Population-guided Novelty Search For Reinforcement Learning In Hard Exploration Environments (2018)7.16
• Novelty Search For Deep Reinforcement Learning Policy Network Weights By Action Sequence Edit Metric Distance (2019)8.09
• Generative Adversarial Exploration For Reinforcement Learning (2022)0.00
• CEM-RL: Combining Evolutionary And Gradient-based Methods For Policy Search (2018)0.00
• Collaborative Evolutionary Reinforcement Learning (2019)0.00