53 citations · 227 across the 20 of their papers we have counts for
22 papers
RMP2: A Structured Composable Policy Class for Robot Learning
Anqi Li, Ching-An Cheng, M. Asif Rana +4
We consider the problem of learning motion policies for acceleration-based robotics systems with a structured policy class specified by RMPflow. RMPflow is a multi-task control fra…
RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies
Ching-An Cheng, Mustafa Mukadam, Jan Issac +4
Generating robot motion for multiple tasks in dynamic environments is challenging, requiring an algorithm to respond reactively while accounting for complex nonlinear relationships…
Explaining Fast Improvement in Online Imitation Learning
Xinyan Yan, Byron Boots, Ching-An Cheng
Online imitation learning (IL) is an algorithmic framework that leverages interactions with expert policies for efficient policy optimization. Here policies are optimized by perfor…
Policy Improvement via Imitation of Multiple Oracles
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
Despite its promise, reinforcement learning's real-world adoption has been hampered by the need for costly exploration to learn a good policy. Imitation learning (IL) mitigates thi…
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
Amir Rahimi, Amirreza Shaban, Ching-An Cheng +2
Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration funct…
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng, Remi Tachet des Combes, Byron Boots +1
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear reg…
Continuous Online Learning and New Insights to Online Imitation Learning
Jonathan Lee, Ching-An Cheng, Ken Goldberg +1
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in pr…
Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
Mustafa Mukadam, Ching-An Cheng, Dieter Fox +2
RMPflow is a recently proposed policy-fusion framework based on differential geometry. While RMPflow has demonstrated promising performance, it requires the user to provide sensibl…
Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Ching-An Cheng, Xinyan Yan, Byron Boots
Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods ar…
Stable, Concurrent Controller Composition for Multi-Objective Robotic Tasks
Anqi Li, Ching-An Cheng, Byron Boots +1
Robotic systems often need to consider multiple tasks concurrently. This challenge calls for controller synthesis algorithms that fulfill multiple control specifications while main…
An Online Learning Approach to Model Predictive Control
Nolan Wagener, Ching-An Cheng, Jacob Sacks +1
Model predictive control (MPC) is a powerful technique for solving dynamic control tasks. In this paper, we show that there exists a close connection between MPC and online learnin…
Online Learning with Continuous Variations: Dynamic Regret and Reductions
Ching-An Cheng, Jonathan Lee, Ken Goldberg +1
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in pr…
RMPflow: A Computational Graph for Automatic Motion Policy Generation
Ching-An Cheng, Mustafa Mukadam, Jan Issac +4
We develop a novel policy synthesis algorithm, RMPflow, based on geometrically consistent transformations of Riemannian Motion Policies (RMPs). RMPs are a class of reactive motion…
Truncated Back-propagation for Bilevel Optimization
Amirreza Shaban, Ching-An Cheng, Nathan Hatch +1
Bilevel optimization has been recently revisited for designing and analyzing algorithms in hyperparameter tuning and meta learning tasks. However, due to its nested structure, eval…
Predictor-Corrector Policy Optimization
Ching-An Cheng, Xinyan Yan, Nathan Ratliff +1
We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that…
Orthogonally Decoupled Variational Gaussian Processes
Hugh Salimbeni, Ching-An Cheng, Byron Boots +1
Gaussian processes (GPs) provide a powerful non-parametric framework for reasoning over functions. Despite appealing theory, its superlinear computational and memory complexities h…
Accelerating Imitation Learning with Predictive Models
Ching-An Cheng, Xinyan Yan, Evangelos A. Theodorou +1
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has p…
Fast Policy Learning through Imitation and Reinforcement
Ching-An Cheng, Xinyan Yan, Nolan Wagener +1
Imitation learning (IL) consists of a set of tools that leverage expert demonstrations to quickly learn policies. However, if the expert is suboptimal, IL can yield policies with i…
Convergence of Value Aggregation for Imitation Learning
Ching-An Cheng, Byron Boots
Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving…
Variational Inference for Gaussian Process Models with Linear Complexity
Ching-An Cheng, Byron Boots
Large-scale Gaussian process inference has long faced practical challenges due to time and space complexity that is superlinear in dataset size. While sparse variational Gaussian p…
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Yunpeng Pan, Ching-An Cheng, Kamil Saigol +4
We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost sensors. By imitating a model predictive controller equipped with adva…
Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
Mustafa Mukadam, Ching-An Cheng, Xinyan Yan +1
The problem of optimal motion planing and control is fundamental in robotics. However, this problem is intractable for continuous-time stochastic systems in general and the solutio…