A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization

no code implementations • 17 Mar 2024 • Yudong Luo, Yangchen Pan, Han Wang, Philip Torr, Pascal Poupart

Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications.

Benchmarking Constraint Inference in Inverse Reinforcement Learning

2 code implementations • 20 Jun 2022 • Guiliang Liu, Yudong Luo, Ashish Gaurav, Kasra Rezaee, Pascal Poupart

When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints.

Autonomous Driving Benchmarking +2

Distributional Reinforcement Learning with Monotonic Splines

no code implementations • ICLR 2022 • Yudong Luo, Guiliang Liu, Haonan Duan, Oliver Schulte, Pascal Poupart

Distributional Reinforcement Learning (RL) differs from traditional RL by estimating the distribution over returns to capture the intrinsic uncertainty of MDPs.

Distributional Reinforcement Learning reinforcement-learning +1

Learning Selective Communication for Multi-Agent Path Finding

1 code implementation • 12 Sep 2021 • Ziyuan Ma, Yudong Luo, Jia Pan

Learning communication via deep reinforcement learning (RL) or imitation learning (IL) has recently been shown to be an effective way to solve Multi-Agent Path Finding (MAPF).

Imitation Learning Multi-Agent Path Finding +1

Distributed Heuristic Multi-Agent Path Finding with Communication

1 code implementation • 21 Jun 2021 • Ziyuan Ma, Yudong Luo, Hang Ma

The final trained policy is applied to each agent for decentralized execution.

Multi-Agent Path Finding Q-Learning +1