most citedA Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2021★ 2 cited

A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis

Joseph Palermo, Johnny Ye, Alok Singh

We convert the DeepMind Mathematics Dataset into a reinforcement learning environment by interpreting it as a program synthesis problem. Each action taken in the environment adds a…