Publications (13)
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…
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…
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…
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…
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…
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.…
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…
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…
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…
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…
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.…
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.…
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…