MSR Thesis Defense
PhD Student
Robotics Institute,
Carnegie Mellon University

Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation

GHC 4405

Abstract: Recent advances in GPU-based parallel simulation have enabled practitioners to collect large amounts of data and train complex control policies using deep reinforcement learning (RL), on commodity GPUs. However, such successes for RL in robotics have been limited to tasks sufficiently simulated by fast rigid-body dynamics. Simulation techniques for soft bodies are comparatively several [...]