Search Machine Learning Repository:
All publications by Sridhar Mahadevan
authors venues years



Projected Natural Actor-Critic
Philip S. Thomas, William C. Dabney, Stephen Giguere and Sridhar Mahadevan
Advances in Neural Information Processing Systems 26, 2013


Regularized Off-Policy TD-Learning
Bo Liu, Sridhar Mahadevan and Ji Liu
Advances in Neural Information Processing Systems 25, 2012


Basis Construction from Power Series Expansions of Value Functions
Sridhar Mahadevan and Bo Liu
Advances in Neural Information Processing Systems 23, 2010


Manifold alignment using Procrustes analysis
Chang Wang and Sridhar Mahadevan
Proceedings of the 25th International Conference on Machine Learning (ICML-08), 2008


Learning state-action basis functions for hierarchical MDPs
Sarah Osentoski and Sridhar Mahadevan
Proceedings of the 24th International Conference on Machine Learning (ICML-07), 2007


Adaptive mesh compression in 3D computer graphics using multiscale manifold learning
Sridhar Mahadevan
Proceedings of the 24th International Conference on Machine Learning (ICML-07), 2007


Constructing basis functions from directed graphs for value function approximation
Jeffrey Johns and Sridhar Mahadevan
Proceedings of the 24th International Conference on Machine Learning (ICML-07), 2007


Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes
Sridhar Mahadevan and Mauro Maggioni
Journal of Machine Learning Research, 2007


Hierarchical Average Reward Reinforcement Learning
Mohammad Ghavamzadeh and Sridhar Mahadevan
Journal of Machine Learning Research, 2007


Fast direct policy evaluation using multiscale analysis of Markov diffusion processes
Mauro Maggioni and Sridhar Mahadevan
Proceedings of the 23th International Conference on Machine Learning (ICML-06), 2006


Coarticulation: an approach for generating concurrent plans in Markov decision processes
Khashayar Rohanimanesh and Sridhar Mahadevan
Proceedings of the 22nd International Conference on Machine Learning (ICML-05), 2005


Proto-value functions: developmental reinforcement learning
Sridhar Mahadevan
Proceedings of the 22nd International Conference on Machine Learning (ICML-05), 2005


Value Function Approximation with Diffusion Wavelets and Laplacian Eigenfunctions
Sridhar Mahadevan and Mauro Maggioni
Advances in Neural Information Processing Systems 18, 2005


Coarticulation in Markov Decision Processes
Khashayar Rohanimanesh, Robert Platt, Sridhar Mahadevan and Roderic Grupen
Advances in Neural Information Processing Systems 17, 2004


Hierarchical Policy Gradient Algorithms
Mohammad Ghavamzadeh and Sridhar Mahadevan
Proceedings of the 20th International Conference on Machine Learning (ICML-03), 2003


Learning to Take Concurrent Actions
Khashayar Rohanimanesh and Sridhar Mahadevan
Advances in Neural Information Processing Systems 15, 2002