Scheduling Straight-Line Code Using Reinforcement Learning and Rollouts

The execution order of a block of computer instructions can make a difference in its running time by a factor of two or more. In order to achieve the best possible speed, compilers use heuristic schedulers appropriate to each specific architecture implementation. However, these heuristic schedulers are time-consuming and expensive to build. In this paper, we present results using both rollouts and reinforcement learning to construct heuristics for scheduling basic blocks. The rollout scheduler outperformed a commercial scheduler, and the reinforcement learning scheduler performed almost as well as the commercial scheduler.

• Type: Conference
• Year: 1998
• Where: NIPS
• Authors: Amy McGovern, J. Eliot B. Moss
• Keywords: Commercial Scheduler, Heuristic Schedulers, NIPS 1998, NIPS 2007, Reinforcement Learning