Search

Subramanian Ramamoorthy

Bayesian Policy Reuse
Action Priors for Learning Domain Invariances
Adapting Interaction Environments to Diverse Users through Online Action Set Selection
Giving Advice to Agents with Hidden Goals
On User Behaviour Adaptation Under Interface Change
Clustering markov decision processes for continual transfer
Clustering Markov Decision Processes For Continual Transfer
Latent-variable MDP models for adapting the interaction environment of diverse users
What Good are Actions? Accelerating Learning using Learned Action Priors
A Multitask Representation using Reusable Local Policy Templates
Learning Spatial Relationships between Objects
A Game Theoretic Procedure for Learning Hierarchically Structured Strategies

Published with Wowchemy — the free, open source website builder that empowers creators.