VASE: Variational Assorted Surprise Exploration for Reinforcement Learning Oct 31, 2019 continuous-control Continuous Control
— Unverified Continuous Control with Contexts, Provably Oct 30, 2019 continuous-control Continuous Control
— Unverified Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control Oct 28, 2019 continuous-control Continuous Control
— Unverified Better Exploration with Optimistic Actor-Critic Oct 28, 2019 continuous-control Continuous Control
— Unverified Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight Oct 21, 2019 continuous-control Continuous Control
Code Code Available All-Action Policy Gradient Methods: A Numerical Integration Approach Oct 21, 2019 All continuous-control
— Unverified Regularization Matters in Policy Optimization Oct 21, 2019 continuous-control Continuous Control
Code Code Available Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video Oct 21, 2019 continuous-control Continuous Control
Code Code Available Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation Oct 17, 2019 continuous-control Continuous Control
Code Code Available Regularizing Model-Based Planning with Energy-Based Models Oct 12, 2019 continuous-control Continuous Control
— Unverified Ctrl-Z: Recovering from Instability in Reinforcement Learning Oct 9, 2019 continuous-control Continuous Control
— Unverified Policy Optimization Through Approximate Importance Sampling Oct 9, 2019 continuous-control Continuous Control
Code Code Available Multi-step Greedy Reinforcement Learning Algorithms Oct 7, 2019 Continuous Control Game of Go
— Unverified Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling Oct 5, 2019 continuous-control Continuous Control
Code Code Available Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning Oct 2, 2019 continuous-control Continuous Control
— Unverified Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning Oct 1, 2019 continuous-control Continuous Control
Code Code Available Meta-Q-Learning Sep 30, 2019 continuous-control Continuous Control
Code Code Available DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs Sep 28, 2019 Continuous Control
Code Code Available The Differentiable Cross-Entropy Method Sep 27, 2019 BIG-bench Machine Learning continuous-control
Code Code Available CAQL: Continuous Action Q-Learning Sep 26, 2019 continuous-control Continuous Control
— Unverified MERL: Multi-Head Reinforcement Learning Sep 26, 2019 continuous-control Continuous Control
— Unverified V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control Sep 26, 2019 continuous-control Continuous Control
Code Code Available CAPACITY-LIMITED REINFORCEMENT LEARNING: APPLICATIONS IN DEEP ACTOR-CRITIC METHODS FOR CONTINUOUS CONTROL Sep 25, 2019 continuous-control Continuous Control
— Unverified QXplore: Q-Learning Exploration by Maximizing Temporal Difference Error Sep 25, 2019 continuous-control Continuous Control
— Unverified Regulatory Focus: Promotion and Prevention Inclinations in Policy Search Sep 25, 2019 Atari Games continuous-control
— Unverified Policy Optimization In the Face of Uncertainty Sep 25, 2019 continuous-control Continuous Control
— Unverified Advantage Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning Sep 25, 2019 continuous-control Continuous Control
— Unverified Samples Are Useful? Not Always: denoising policy gradient updates using variance explained Sep 25, 2019 continuous-control Continuous Control
— Unverified Model-free Learning Control of Nonlinear Stochastic Systems with Stability Guarantee Sep 25, 2019 continuous-control Continuous Control
— Unverified Safe Policy Learning for Continuous Control Sep 25, 2019 continuous-control Continuous Control
— Unverified Towards Simplicity in Deep Reinforcement Learning: Streamlined Off-Policy Learning Sep 25, 2019 continuous-control Continuous Control
— Unverified Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning Sep 25, 2019 continuous-control Continuous Control
— Unverified Learning Functionally Decomposed Hierarchies for Continuous Navigation Tasks Sep 25, 2019 continuous-control Continuous Control
— Unverified ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots Sep 25, 2019 continuous-control Continuous Control
Code Code Available Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning Sep 23, 2019 continuous-control Continuous Control
Code Code Available Meta-Inverse Reinforcement Learning with Probabilistic Context Variables Sep 20, 2019 continuous-control Continuous Control
Code Code Available How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning? Sep 20, 2019 continuous-control Continuous Control
— Unverified Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning Sep 17, 2019 continuous-control Continuous Control
— Unverified Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space Sep 15, 2019 continuous-control Continuous Control
— Unverified Biased Estimates of Advantages over Path Ensembles Sep 15, 2019 Atari Games continuous-control
— Unverified Driving in Dense Traffic with Model-Free Reinforcement Learning Sep 15, 2019 continuous-control Continuous Control
Code Code Available VILD: Variational Imitation Learning with Diverse-quality Demonstrations Sep 15, 2019 continuous-control Continuous Control
— Unverified Deterministic Value-Policy Gradients Sep 9, 2019 continuous-control Continuous Control
— Unverified Learning Action-Transferable Policy with Action Embedding Sep 5, 2019 Continuous Control Reinforcement Learning
Code Code Available Generalization in Transfer Learning Sep 3, 2019 continuous-control Continuous Control
— Unverified Dynamics-aware Embeddings Aug 25, 2019 continuous-control Continuous Control
Code Code Available Model-based Lookahead Reinforcement Learning Aug 15, 2019 continuous-control Continuous Control
— Unverified Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach Aug 14, 2019 continuous-control Continuous Control
— Unverified Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics Aug 13, 2019 continuous-control Continuous Control
— Unverified Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning Aug 6, 2019 continuous-control Continuous Control
— Unverified 