69 citations · 83 across the 6 of their papers we have counts for
3 papers · 1 filter
Large-Scale Multi-Agent Deep FBSDEs
Tianrong Chen, Ziyi Wang, Ioannis Exarchos +1
In this paper we present a scalable deep learning framework for finding Markovian Nash Equilibria in multi-agent stochastic games using fictitious play. The motivation is inspired…
Policy Transfer via Kinematic Domain Randomization and Adaptation
Ioannis Exarchos, Yifeng Jiang, Wenhao Yu +1
Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simpl…
Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
Marcus Aloysius Pereira, Ziyi Wang, Ioannis Exarchos +1
This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints. The pr…