On overfitting and asymptotic bias in batch reinforcement learning with
partial observability

On overfitting and asymptotic bias in batch reinforcement learning with partial observability

22 September 2017

Vincent François-Lavet

Guillaume Rabusseau

Papers citing "On overfitting and asymptotic bias in batch reinforcement learning with partial observability"

12 / 12 papers shown

Title
Near Optimal Behavior via Approximate State Abstraction David Abel D Ellis Hershkowitz Michael L. Littman OffRL 67 164 0 15 Jan 2017
Understanding deep learning requires rethinking generalization Chiyuan Zhang Samy Bengio Moritz Hardt Benjamin Recht Oriol Vinyals HAI 318 4,624 0 10 Nov 2016
Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning Philip S. Thomas Emma Brunskill OffRL 365 576 0 04 Apr 2016
How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies Vincent François-Lavet R. Fonteneau D. Ernst 49 111 0 07 Dec 2015
Net2Net: Accelerating Learning via Knowledge Transfer Tianqi Chen Ian Goodfellow Jonathon Shlens 145 667 0 18 Nov 2015
Doubly Robust Off-policy Value Evaluation for Reinforcement Learning Nan Jiang Lihong Li OffRL 186 623 0 11 Nov 2015
Deep Recurrent Q-Learning for Partially Observable MDPs Matthew J. Hausknecht Peter Stone 104 1,677 0 23 Jul 2015
Extreme State Aggregation Beyond MDPs Marcus Hutter 112 23 0 12 Jul 2014
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning R. Ortner Odalric-Ambrym Maillard D. Ryabko 136 27 0 12 May 2014
Selecting the State-Representation in Reinforcement Learning Odalric-Ambrym Maillard Rémi Munos D. Ryabko 57 40 0 11 Feb 2013
Predictive State Representations: A New Theory for Modeling Dynamical Systems Satinder Singh Michael R. James Matthew R. Rudary AI4TS AI4CE 86 288 0 11 Jul 2012
Metrics for Finite Markov Decision Processes N. Ferns Prakash Panangaden Doina Precup 74 320 0 11 Jul 2012