4 papers
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
Lakshita Dodeja, Ondrej Biza, Shivam Vats +5
Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been…
Accelerating Residual Reinforcement Learning with Uncertainty Estimation
Lakshita Dodeja, Karl Schmeckpeper, Shivam Vats +4
Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residu…
Towards the design of user-centric strategy recommendation systems for collaborative Human-AI tasks
Lakshita Dodeja, Pradyumna Tambwekar, Erin Hedlund-Botti +1
Artificial Intelligence is being employed by humans to collaboratively solve complicated tasks for search and rescue, manufacturing, etc. Efficient teamwork can be achieved by unde…
A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting
Pradyumna Tambwekar, Lakshita Dodeja, Nathan Vaska +2
Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling hum…