The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions, which are usually sparse, often lead to inefficient or suboptimal policies, misalignment with user values, or difficulties in attributing credit or blame within multi-agent systems. Reinforcement learning from human feedback is a successful technique that can mitigate such issues [...]

Abstract: With the growing accessibility of humanoid hardware and rapid advances in foundation models, we are entering an era where achieving general embodied intelligence is within reach—enabling humanoid robots to perform a wide range of tasks in human-centric environments. Despite significant progress in language and vision foundation models, controlling humanoids with high degrees of freedom [...]

Abstract: How do we teach humanoid robots to move like humans—and do so reliably in the real world? In this talk, I’ll share my journey in building a learning-based pipeline that closes the loop between simulation and reality for humanoid whole-body control. Starting from real-time teleoperation (H2O), to scalable data humanoid collection (OmniH2O), to learning [...]