Portrait of Matthew Riemer is unavailable

Matthew Riemer

PhD - Université de Montréal
Supervisor
Irina Rish
Co-supervisor
Irina Rish
Research Topics
Reinforcement Learning

Publications

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Matthew Riemer
Gopeshh Raaj Subbaraj
Glen Berseth
Irina Rish
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (see more)y minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pok\'emon and Tetris.
2024-12-18
ArXiv (preprint)
doi.org
arxiv.org
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Matthew Riemer
Gopeshh Raaj Subbaraj
Glen Berseth
Irina Rish
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (see more)y minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pok\'emon and Tetris.
2024-12-18
ArXiv (preprint)
arxiv.org
arxiv.org