Search Machine Learning Repository:
All publications by Philip S. Thomas
authors venues years



Policy Evaluation Using the \Omega -Return
Philip S. Thomas, Scott Niekum, Georgios Theocharous and George Konidaris
Advances in Neural Information Processing Systems 28, 2015


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


TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning
George Konidaris, Scott Niekum and Philip S. Thomas
Advances in Neural Information Processing Systems 24, 2011


Policy Gradient Coagent Networks
Philip S. Thomas
Advances in Neural Information Processing Systems 24, 2011


Conjugate Markov Decision Processes
Philip S. Thomas and Andrew G. Barto
Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011