Deep RL

Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation AAAI 2021 The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning NeurIPS 2021 The Value-Improvement Path: Towards Better Representations for Reinforcement Learning AAAI 2021 Time-Constrained Multi-Agent Path Finding in Non-Lattice Graphs with Deep Reinforcement Learning ACML 2021 Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods NeurIPS 2021 TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting EMNLP 2021 Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach EMNLP 2021 Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing ICML 2021 Towards Deeper Deep Reinforcement Learning with Spectral Normalization NeurIPS 2021 Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning AAAI 2021 Towards mental time travel: a hierarchical memory for reinforcement learning agents NeurIPS 2021 Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion CoRL 2021 Towards Robust Bisimulation Metric Learning NeurIPS 2021 Towards Sample Efficient Agents through Algorithmic Alignment (Student Abstract) AAAI 2021 Towards Tight Bounds on the Sample Complexity of Average-reward MDPs ICML 2021 Towards tractable optimism in model-based reinforcement learning UAI 2021 Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization NeurIPS 2021 Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery AAAI 2021 Transient Non-stationarity and Generalisation in Deep Reinforcement Learning ICLR 2021 Turn-Level User Satisfaction Estimation in E-commerce Customer Service ACL 2021 UCB Momentum Q-learning: Correcting the bias without forgetting ICML 2021 Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach AAAI 2021 Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization NeurIPS 2021 Understanding the World Through Action CoRL 2021 UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning ICML 2021