Chris Lu

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Learning mirror maps in policy mirror descent

Can Learned Optimization Make Reinforcement Learning Less Difficult?

Discovering Temporally-Aware Reinforcement Learning Algorithms

Behaviour Distillation

Discovering Preference Optimization Algorithms with and for Large Language Models

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

Recurrent Reinforcement Learning with Memoroids

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

EvIL: Evolution Strategies for Generalisable Imitation Learning

Discovering Minimal Reinforcement Learning Environments