102 citations · 207 across the 33 of their papers we have counts for
7 papers · 1 filter
Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models
Farnam Mansouri, Yuxin Chen, Ara Vartanian +2
Algorithmic machine teaching studies the interaction between a teacher and a learner where the teacher selects labeled examples aiming at teaching a target hypothesis. In a quest t…
Towards Deployment of Robust AI Agents for Human-Machine Partnerships
Ahana Ghosh, Sebastian Tschiatschek, Hamed Mahdavi +1
We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent,…
Can A User Anticipate What Her Followers Want?
Abir De, Adish Singla, Utkarsh Upadhyay +1
Whenever a social media user decides to share a story, she is typically pleased to receive likes, comments, shares, or, more generally, feedback from her followers. As a result, sh…
Interactive Teaching Algorithms for Inverse Reinforcement Learning
Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher +1
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorith…
Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
Sebastian Tschiatschek, Ahana Ghosh, Luis Haug +2
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner…
Unifying Ensemble Methods for Q-learning via Social Choice Theory
Rishav Chourasia, Adish Singla
Ensemble methods have been widely applied in Reinforcement Learning (RL) in order to enhance stability, increase convergence speed, and improve exploration. These methods typically…