← Methods
Reinforcement Learning › Methods ›

Deep RL

3861 directly classified papers

Papers per year

Papers

On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization NIPS 2012
Regularized Off-Policy TD-Learning NIPS 2012
On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes NIPS 2012
Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress NIPS 2012
Value Pursuit Iteration NIPS 2012
Exploration in Relational Domains for Model-based Reinforcement Learning JMLR 2012
Non-parametric Approximate Dynamic Programming via the Kernel Method NIPS 2012
Sketch-Based Linear Value Function Approximation NIPS 2012
Tendon-Driven Variable Impedance Control Using Reinforcement Learning RSS 2012
Hierarchical Optimistic Region Selection driven by Curiosity NIPS 2012
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning NIPS 2012
Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems NIPS 2012
Algorithms for Learning Markov Field Policies NIPS 2012
Weighted Likelihood Policy Search with Model Selection NIPS 2012
Tractable Objectives for Robust Policy Optimization NIPS 2012
Learning to Agglomerate Superpixel Hierarchies NIPS 2011
Action-Gap Phenomenon in Reinforcement Learning NIPS 2011
The Fixed Points of Off-Policy TD NIPS 2011
Transfer from Multiple MDPs NIPS 2011
Agnostic KWIK learning and efficient approximate reinforcement learning COLT 2011
Generalized TD Learning JMLR 2011
Robust Approximate Bilinear Programming for Value Function Approximation JMLR 2011
Policy Gradient Coagent Networks NIPS 2011
Continuous Rapid Action Value Estimates ACML 2011
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning RSS 2011