Distributed RL
2019-11 DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
2020-10 Massively Large-Scale Distributed Reinforcement Learning with Menger
그 외 참고
2024-03 DiPaCo: Distributed Path Composition
2024-01 Asynchronous Local-SGD Training for Language Modeling
2023-12 DiLoCo: Distributed Low-Communication Training of Language Models