6 citations · 9 across the 2 of their papers we have counts for
3 papers
cs.AI2020★ 3 cited
Realistic Physics Based Character Controller
Joe Booth, Vladimir Ivanov
Over the course of the last several years there was a strong interest in application of modern optimal control techniques to the field of character animation. This interest was fue…
cs.LG2019
PPO Dash: Improving Generalization in Deep Reinforcement Learning
Joe Booth
Deep reinforcement learning is prone to overfitting, and traditional benchmarks such as Atari 2600 benchmark can exacerbate this problem. The Obstacle Tower Challenge addresses thi…
cs.AI2019★ 6 cited
Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine
Joe Booth, Jackson Booth
Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors us…