reinforcement learning

High-Confidence Off-Policy (or Counterfactual) Variance Estimation AAAI 2021 Hindsight Trust Region Policy Optimization IJCAI 2021 Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation NeurIPS 2021 How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control? L4DC 2021 How RL Agents Behave When Their Actions Are Modified AAAI 2021 How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds NAACL 2021 Hybrid Summarization with Semantic Weighting Reward and Latent Structure Detector ACML 2021 Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels ICLR 2021 Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management NAACL 2021 Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path NeurIPS 2021 Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning EACL 2021 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning ICML 2021 Improved Regret Bound and Experience Replay in Regularized Policy Iteration ICML 2021 Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration AAAI 2021 Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation NAACL 2021 Improving Factual Consistency Between a Response and Persona Facts EACL 2021 Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning NAACL 2021 Improving Sample Efficiency in Model-Free Reinforcement Learning from Images AAAI 2021 Independence-aware Advantage Estimation IJCAI 2021 Infinite Time Horizon Safety of Bayesian Neural Networks NeurIPS 2021 Intelligent and Learning Agents: Four Investigations IJCAI 2021 Interaction-Grounded Learning ICML 2021 Interactive Learning from Activity Description ICML 2021 Interactive Machine Comprehension with Dynamic Knowledge Graphs EMNLP 2021 Interesting Object, Curious Agent: Learning Task-Agnostic Exploration NeurIPS 2021