7 papers
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…
Asymptotically Optimal Ergodic Coverage on Generalized Motion Fields
Christian Hughes, Yilang Liu, Yanis Lahrach +6
Autonomous robotic exploration in remote and extreme environments allows scientists to model complex transport phenomena and collective behaviors described by continuously deformin…
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…
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…
A novel parallelizable convergence accelerating method: Pointwise Frequency Damping
Zikun Liu, Xukun Wang, Yilang Liu +1
This paper proposes a novel class of data-driven acceleration methods for steady-state flow field solvers. The core innovation lies in predicting and assigning the asymptotic limit…
A data-driven convergence booster for accelerating and stabilizing pseudo time-stepping
Xukun Wang, Yilang Liu, Xiang Yang +1
This paper introduces a novel data-driven convergence booster that not only accelerates convergence but also stabilizes solutions in cases where obtaining a steady-state solution i…