papers

Publications (13)

cs.RO2017

Comparing Human-Centric and Robot-Centric Sampling for Robot Deep Learning from Demonstrations

Michael Laskey, Caleb Chuck, Jonathan Lee +5

Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations. "Human-Centric" (HC) samp…

cs.AI2026

Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL

Sarthak Dayal, Abhinav Peri, Carl Qi +4

Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and re…

cs.RO2021

ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory

Ajinkya Jain, Rudolf Lioutikov, Caleb Chuck +1

Robots in human environments will need to interact with a wide variety of articulated objects such as cabinets, drawers, and dishwashers while assisting humans in performing day-to…

cs.AI2024

Automated Discovery of Functional Actual Causes in Complex Environments

Caleb Chuck, Sankaran Vaidyanathan, Stephen Giguere +3

Reinforcement learning (RL) algorithms often struggle to learn policies that generalize to novel situations due to issues such as causal confusion, overfitting to irrelevant factor…

cs.RO2026

Learning Object Manipulation from Scratch via Contrastive Interaction

Tongle Shen, Caleb Chuck, Fan Feng +1

Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured representations of the dynamics. Howeve…

cs.AI2024

Granger Causal Interaction Skill Chains

Caleb Chuck, Kevin Black, Aditya Arjun +2

Reinforcement Learning (RL) has demonstrated promising results in learning policies for complex tasks, but it often suffers from low sample efficiency and limited transferability.…

cs.LG2024

A Dual Approach to Imitation Learning from Observations with Offline Datasets

Harshit Sikchi, Caleb Chuck, Amy Zhang +1

Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. However, demonstrating expert beha…

cs.LG2024

Learning Action-based Representations Using Invariance

Max Rudolph, Caleb Chuck, Kevin Black +3

Robust reinforcement learning agents using high-dimensional observations must be able to identify relevant state features amidst many exogeneous distractors. A representation that…

cs.AI2025

RLZero: Direct Policy Inference from Language Without In-Domain Supervision

Harshit Sikchi, Siddhant Agarwal, Pranaya Jajoo +6

The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward sign…

cs.RO2024

Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning

Caleb Chuck, Carl Qi, Michael J. Munje +13

Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might f…

cs.LG2020

Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Caleb Chuck, Supawit Chockchowwat, Scott Niekum

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation.…

cs.LG2025

Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning

Caleb Chuck, Fan Feng, Carl Qi +4

Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion.…

cs.LG2024

SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions

Zizhao Wang, Jiaheng Hu, Caleb Chuck +5

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised…