{"total":54,"rows":[{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2109.06449","title":"Deep hierarchical reinforcement agents for automated penetration testing","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2110.15481","title":"Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning","created":"2021-10-29","cited_by_count":19,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2201.09058","title":"DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities","created":"2021-12-15","cited_by_count":15,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2109.09478","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2109.09968","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","created":"2021-09-21","cited_by_count":11,"area":null},{"id":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2210.07382","title":"Behavior Cloned Transformers are Neurosymbolic Reasoners","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2102.11329","title":"Action Redundancy in Reinforcement Learning","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2110.08470","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","created":"2021-10-16","cited_by_count":8,"area":null},{"id":"2204.02558","title":"DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2201.00354","title":"Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference","created":"2022-01-02","cited_by_count":6,"area":null},{"id":"2312.02561","title":"DanZero+: Dominating the GuanDan Game through Reinforcement Learning","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2106.06768","title":"Planning Spatial Networks with Monte Carlo Tree Search","created":"2021-06-12","cited_by_count":5,"area":null},{"id":"2210.17087","title":"DanZero: Mastering GuanDan Game with Reinforcement Learning","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2206.02733","title":"Deep Reinforcement Learning for Cybersecurity Threat Detection and Protection: A Review","created":"2022-06-06","cited_by_count":4,"area":null},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2109.10632","title":"Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning","created":"2021-09-22","cited_by_count":3,"area":null},{"id":"2112.14553","title":"Active Learning of Quantum System Hamiltonians yields Query Advantage","created":"2021-12-29","cited_by_count":3,"area":null},{"id":"2204.13971","title":"Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2403.10692","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2103.09977","title":"Situated Language Learning via Interactive Narratives","created":"2021-03-18","cited_by_count":2,"area":null},{"id":"2107.05181","title":"AoI-minimizing Scheduling in UAV-relayed IoT Networks","created":"2021-07-12","cited_by_count":2,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2210.15670","title":"Knowledge-Guided Exploration in Deep Reinforcement Learning","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2303.09628","title":"Efficient Learning of High Level Plans from Play","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2104.11918","title":"Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction","created":"2021-04-24","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2203.09565","title":"Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2209.04105","title":"An Analysis of Deep Reinforcement Learning Agents for Text-based Games","created":"2022-09-09","cited_by_count":1,"area":null},{"id":"2209.08206","title":"Selective Token Generation for Few-shot Natural Language Generation","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2510.00480","title":"Expandable Decision-Making States for Multi-Agent Deep Reinforcement Learning in Soccer Tactical Analysis","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2112.06055","title":"Towards Autonomous Satellite Communications: An AI-based Framework to Address System-level Challenges","created":"2021-12-11","cited_by_count":0,"area":null},{"id":"2112.12458","title":"Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning","created":"2021-12-23","cited_by_count":0,"area":null},{"id":"2203.04227","title":"A Practical AoI Scheduler in IoT Networks with Relays","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2211.15589","title":"Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2306.15913","title":"DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2505.20110","title":"Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.36672","title":"Human-inspired, Task-Dimension-Guided Exploration for Efficient Learning in High Dimensions","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}