Deep RL

Inverse Reinforcement Learning with Locally Consistent Reward Functions NeurIPS 2015 Learning Continuous Control Policies by Stochastic Value Gradients NeurIPS 2015 Off-policy Model-based Learning under Unknown Factored Dynamics ICML 2015 On Convergence of Emphatic Temporal-Difference Learning COLT 2015 On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence ICML 2015 On the Rate of Convergence and Error Bounds for LSTD(λ) ICML 2015 Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation ACML 2015 Universal Value Function Approximators ICML 2015 Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning NeurIPS 2015 Algorithms for CVaR Optimization in MDPs NeurIPS 2014 A new Q(lambda) with interim forward view and Monte Carlo equivalence ICML 2014 Bayes-Adaptive Simulation-based Search with Value Function Approximation NeurIPS 2014 Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning NeurIPS 2014 Difference of Convex Functions Programming for Reinforcement Learning NeurIPS 2014 How hard is my MDP?" The distribution-norm to the rescue" NeurIPS 2014 Learning Complex Neural Network Policies with Trajectory Optimization ICML 2014 Online Multi-Task Learning for Policy Gradient Methods ICML 2014 Optimistic Planning in Markov Decision Processes Using a Generative Model NeurIPS 2014 Quasi Newton Temporal Difference Learning ACML 2014 RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning NeurIPS 2014 Recurrent Models of Visual Attention NeurIPS 2014 Reinforcement learning with value advice ACML 2014 Sample Efficient Reinforcement Learning with Gaussian Processes ICML 2014 Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations ICML 2014 Sequential crowdsourced labeling as an epsilon-greedy exploration in a Markov Decision Process AISTATS 2014