Policy Optimization for H_2 Linear Control with H_ Robustness Guarantee: Implicit Regularization and Global Convergence Jun 8, 2020 Reinforcement Learning (RL)
— Unverified Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands Jun 8, 2020 Model-based Reinforcement Learning Reinforcement Learning (RL)
Code Code Available Online Data Poisoning Attacks Jun 8, 2020 Data Poisoning Deep Reinforcement Learning
— Unverified Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems Jun 8, 2020 reinforcement-learning Reinforcement Learning (RL)
— Unverified Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors Jun 8, 2020 model Model-based Reinforcement Learning
— Unverified Balancing a CartPole System with Reinforcement Learning -- A Tutorial Jun 8, 2020 OpenAI Gym Q-Learning
— Unverified Conservative Q-Learning for Offline Reinforcement Learning Jun 8, 2020 continuous-control Continuous Control
Code Code Available A Comparison of Self-Play Algorithms Under a Generalized Framework Jun 8, 2020 Reinforcement Learning (RL)
— Unverified A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning Jun 8, 2020 Atari Games Multi-Task Learning
— Unverified Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models Jun 8, 2020 Reinforcement Learning (RL)
— Unverified A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret Jun 8, 2020 Q-Learning reinforcement-learning
— Unverified Learning to Play No-Press Diplomacy with Best Response Policy Iteration Jun 8, 2020 Deep Reinforcement Learning Reinforcement Learning (RL)
Code Code Available Stable Reinforcement Learning with Unbounded State Space Jun 8, 2020 reinforcement-learning Reinforcement Learning
— Unverified Reinforcement Learning Under Moral Uncertainty Jun 8, 2020 Autonomous Vehicles BIG-bench Machine Learning
Code Code Available Randomized Policy Learning for Continuous State and Action MDPs Jun 8, 2020 Deep Reinforcement Learning Reinforcement Learning (RL)
— Unverified Skill Discovery of Coordination in Multi-agent Reinforcement Learning Jun 7, 2020 Diversity Multi-agent Reinforcement Learning
— Unverified Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains Jun 7, 2020 Decision Making Hierarchical Reinforcement Learning
Code Code Available Real-Time Model Calibration with Deep Reinforcement Learning Jun 7, 2020 Deep Reinforcement Learning model
— Unverified Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping Jun 7, 2020 Object Object Tracking
— Unverified Efficient Poverty Mapping using Deep Reinforcement Learning Jun 7, 2020 Deep Reinforcement Learning object-detection
— Unverified Dual Policy Distillation Jun 7, 2020 continuous-control Continuous Control
Code Code Available Implications of Human Irrationality for Reinforcement Learning Jun 7, 2020 BIG-bench Machine Learning Decision Making
— Unverified Incorporating Pragmatic Reasoning Communication into Emergent Language Jun 7, 2020 Multi-agent Reinforcement Learning Reinforcement Learning (RL)
— Unverified Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning Jun 7, 2020 counterfactual Multi-agent Reinforcement Learning
Code Code Available Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning Jun 6, 2020 Off-policy evaluation reinforcement-learning
— Unverified Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity Jun 6, 2020 reinforcement-learning Reinforcement Learning (RL)
— Unverified Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity Jun 6, 2020 reinforcement-learning Reinforcement Learning (RL)
Code Code Available Stable and Efficient Policy Evaluation Jun 6, 2020 Reinforcement Learning (RL)
— Unverified State Action Separable Reinforcement Learning Jun 5, 2020 Decision Making reinforcement-learning
— Unverified AutoHAS: Efficient Hyperparameter and Architecture Search Jun 5, 2020 AutoML Hyperparameter Optimization
— Unverified Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization Jun 5, 2020 Offline RL reinforcement-learning
Code Code Available Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent Jun 5, 2020 reinforcement-learning Reinforcement Learning
Code Code Available Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval Jun 5, 2020 Information Retrieval reinforcement-learning
— Unverified Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion Jun 4, 2020 reinforcement-learning Reinforcement Learning
Code Code Available Meta-Model-Based Meta-Policy Optimization Jun 4, 2020 continuous-control Continuous Control
— Unverified Single-step deep reinforcement learning for open-loop control of laminar and turbulent flows Jun 4, 2020 Deep Reinforcement Learning Reinforcement Learning (RL)
Code Code Available Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning Jun 4, 2020 Deep Reinforcement Learning reinforcement-learning
Code Code Available Refined Continuous Control of DDPG Actors via Parametrised Activation Jun 4, 2020 continuous-control Continuous Control
— Unverified Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty Jun 4, 2020 reinforcement-learning Reinforcement Learning
— Unverified A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines Jun 4, 2020 Q-Learning reinforcement-learning
Code Code Available Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains Jun 3, 2020 Autonomous Driving Causal Inference
— Unverified Interferobot: aligning an optical interferometer by a reinforcement learning agent Jun 3, 2020 Deep Reinforcement Learning reinforcement-learning
Code Code Available Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging Jun 3, 2020 compressed sensing Computed Tomography (CT)
— Unverified The Value-Improvement Path: Towards Better Representations for Reinforcement Learning Jun 3, 2020 Atari Games reinforcement-learning
— Unverified Temporally-Extended ε-Greedy Exploration Jun 2, 2020 Reinforcement Learning (RL)
Code Code Available Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent Jun 2, 2020 Deep Reinforcement Learning Policy Gradient Methods
Code Code Available Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration Jun 2, 2020 Diversity Efficient Exploration
Code Code Available Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization Jun 2, 2020 Combinatorial Optimization Deep Reinforcement Learning
Code Code Available Active Vision for Early Recognition of Human Actions Jun 1, 2020 reinforcement-learning Reinforcement Learning (RL)
— Unverified Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning Jun 1, 2020 Face Recognition Fairness
— Unverified 