2 papers
cs.LG2025
Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning
Matyáš Lorenc, Roman Neruda
In this paper, we experiment with novelty-based variants of OpenAI-ES, the NS-ES and NSR-ES algorithms, and evaluate their effectiveness in training complex, transformer-based arch…
cs.LG2025
Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning
Matyáš Lorenc, Roman Neruda
We explore the capability of evolution strategies to train an agent with a policy based on a transformer architecture in a reinforcement learning setting. We performed experiments…