9 papers
Gen2Dex: Learning Dexterous Manipulation from Simulation-Initialized Generated Video Demonstrations
Xiaowen Qiu, Yian Wang, Haoxiang You +1
Human video demonstrations provide rich manipulation strategies for dexterous manipulation learning. We study a setting in which a fully specified simulated scene is used to genera…
EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
Haoxiang You, Zeyu Shen, Yilang Liu +16
We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we d…
Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control
Yilang Liu, Haoxiang You, Qian Wang +2
Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order…
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
Haoxiang You, Yilang Liu, Davis Zong +5
We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end withi…
Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
Qi Wang, Mian Wu, Yuyang Zhang +7
Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Des…
Sample-Based Hybrid Mode Control: Asymptotically Optimal Switching of Algorithmic and Non-Differentiable Control Modes
Yilang Liu, Haoxiang You, Ian Abraham
This paper investigates a sample-based solution to the hybrid mode control problem across non-differentiable and algorithmic hybrid modes. Our approach reasons about a set of hybri…
Beyond Smoothness and Convexity: Optimization via sampling
Nahom Seyoum, Haoxiang You
This work explores a novel perspective on solving nonconvex and nonsmooth optimization problems by leveraging sampling based methods. Instead of treating the objective function pur…
Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
Haoxiang You, Yilang Liu, Ian Abraham
In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our…
Is Bellman Equation Enough for Learning Control?
Haoxiang You, Lekan Molu, Ian Abraham
The Bellman equation and its continuous-time counterpart, the Hamilton-Jacobi-Bellman (HJB) equation, serve as necessary conditions for optimality in reinforcement learning and opt…