Satinder Singh Baveja

Publications by Year

Research Areas

Reinforcement Learning in Robotics, Multimodal Machine Learning Applications, Domain Adaptation and Few-Shot Learning, Data Stream Mining Techniques, Gaussian Processes and Bayesian Inference

Most-Cited Works

• → Multi-Stage Attack Graph Security Games(2017)28 cited
• → Human-Timescale Adaptation in an Open-Ended Task Space(2023)22 cited
• Exponential Family Predictive Representations of State(2007)
• The optimal reward problem: designing effective reward for bounded agents(2011)
• Using predictions for planning and modeling in *stochastic environments.(2005)
• On predictive linear gaussian models(2009)
• → Vision-Language Models as a Source of Rewards(2023)3 cited
• Modeling temporal structure of time series with hidden markov experts(1998)
• → Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks(2021)1 cited
• → SIMA 2: A Generalist Embodied Agent for Virtual Worlds(2025)