Arthur Flajolet

Fast Population-Based Reinforcement Learning on a Single Machine

2022 · arXiv (Cornell University)

Training populations of agents has demonstrated great promise in Reinforcement Learning for stabilizing training, improving exploration and asymptotic performance, and generating a diverse set of solutions. However, population-based training is often not considered by practitioners …

PASTA: Pretrained Action-State Transformer Agents

2023 · arXiv (Cornell University)

Self-supervised learning has brought about a revolutionary paradigm shift in various computing domains, including NLP, vision, and biology. Recent approaches involve pre-training transformer models on vast amounts of unlabeled data, serving as a starting point …