← Keywords

function approximation

319 papers

Explore in graph

Co-occurring keywords

reinforcement learning (4122) regret bound (1918) markov decision process (788) sample complexity (1158) neural network (6616) temporal difference learning (149) value function (294) offline reinforcement learning (492) deep reinforcement learning (903) value iteration (162)

Papers

Bellman-consistent Pessimism for Offline Reinforcement Learning NIPS 2021
BooVI: Provably Efficient Bootstrapped Value Iteration NIPS 2021
Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation NIPS 2021
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection NIPS 2021
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NIPS 2021
Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL NIPS 2021
Safe Policy Optimization with Local Generalized Linear Function Approximations NIPS 2021
The Difficulty of Passive Learning in Deep Reinforcement Learning NIPS 2021
Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback NIPS 2021
Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration NIPS 2021
Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization NIPS 2021
Self-Consistent Models and Values NIPS 2021
Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning NIPS 2021
On the Approximation Power of Two-Layer Networks of Random ReLUs COLT 2021
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective COLT 2021
Provable Memorization via Deep Neural Networks using Sub-linear Parameters COLT 2021
Maximum-and-Concatenation Networks ICML 2020
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration AISTATS 2020
Nonlinear System Identification via Tensor Completion AAAI 2020
Black-Box Methods for Restoring Monotonicity ICML 2020
A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms NIPS 2020
On Simulation and Trajectory Prediction with Gaussian Process Dynamics L4DC 2020
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes COLT 2020
Count-Based Exploration with the Successor Representation AAAI 2020
On the Role of Weight Sharing During Deep Option Learning AAAI 2020