{"total":161,"rows":[{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"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":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2104.07886","title":"Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks","created":"2021-04-16","cited_by_count":38,"area":null},{"id":"2111.03466","title":"Learning Large Neighborhood Search Policy for Integer Programming","created":"2021-11-01","cited_by_count":35,"area":null},{"id":"2406.07904","title":"Grounding Multimodal Large Language Models in Actions","created":"2024-06-12","cited_by_count":35,"area":"mllm"},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"area":null},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2110.02128","title":"NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2405.01155","title":"SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints","created":"2024-05-02","cited_by_count":26,"area":null},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24,"area":null},{"id":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2410.04542","title":"Generative Flows on Synthetic Pathway for Drug Design","created":"2024-10-06","cited_by_count":20,"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":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2410.17351","title":"Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","cited_by_count":15,"area":"diffusion"},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2111.10476","title":"Towards Return Parity in Markov Decision Processes","created":"2021-11-19","cited_by_count":13,"area":null},{"id":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"area":null},{"id":"2205.03793","title":"Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces","created":"2022-05-08","cited_by_count":12,"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":"2205.06111","title":"Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2311.15341","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2104.10406","title":"Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching","created":"2021-04-21","cited_by_count":8,"area":null},{"id":"1905.09700","title":"Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces","created":"2019-05-23","cited_by_count":7,"area":"offlinerl"},{"id":"2102.07210","title":"Reversible Action Design for Combinatorial Optimization with Reinforcement Learning","created":"2021-02-14","cited_by_count":7,"area":null},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2111.01294","title":"Learning to Operate an Electric Vehicle Charging Station Considering Vehicle-grid Integration","created":"2021-11-01","cited_by_count":7,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2505.19053","title":"Structured Reinforcement Learning for Combinatorial Decision-Making","created":"2025-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2101.07399","title":"Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination","created":"2021-01-19","cited_by_count":6,"area":null},{"id":"2104.13617","title":"End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning","created":"2021-04-28","cited_by_count":6,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2202.04849","title":"SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2202.08812","title":"Should I send this notification? Optimizing push notifications decision making by modeling the future","created":"2022-02-17","cited_by_count":6,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","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":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"id":"2606.02355","title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training","created":"2026-06-01","cited_by_count":6,"area":"agents"},{"id":"2106.06768","title":"Planning Spatial Networks with Monte Carlo Tree Search","created":"2021-06-12","cited_by_count":5,"area":null},{"id":"2107.04163","title":"Towards Robust Active Feature Acquisition","created":"2021-07-09","cited_by_count":5,"area":null},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2408.01248","title":"Deep progressive reinforcement learning-based flexible resource scheduling framework for IRS and UAV-assisted MEC system","created":"2024-08-02","cited_by_count":5,"area":"deeprl"},{"id":"2503.01919","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","created":"2025-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2208.05327","title":"Fast Offline Policy Optimization for Large Scale Recommendation","created":"2022-08-08","cited_by_count":4,"area":"offlinerl"},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2108.03978","title":"VeRLPy: Python Library for Verification of Digital Designs with Reinforcement Learning","created":"2021-08-09","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":"2201.02058","title":"Sales Time Series Analytics Using Deep Q-Learning","created":"2022-01-06","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":"2208.04537","title":"Automating DBSCAN via Deep Reinforcement Learning","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2211.02296","title":"Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2304.00873","title":"Action Pick-up in Dynamic Action Space Reinforcement Learning","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2305.07069","title":"Deep Reinforcement Learning for Interference Management in UAV-based 3D Networks: Potentials and Challenges","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2310.05170","title":"DeepQTest: Testing Autonomous Driving Systems with Reinforcement Learning and Real-world Weather Data","created":"2023-10-08","cited_by_count":3,"area":"driving"},{"id":"2404.04772","title":"Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning","created":"2024-04-07","cited_by_count":3,"area":"deeprl"},{"id":"2405.16854","title":"Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"agents"},{"id":"2406.02044","title":"Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA","created":"2024-06-04","cited_by_count":3,"area":"safety"},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2410.21151","title":"BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces","created":"2024-10-28","cited_by_count":3,"area":"offlinerl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2506.16429","title":"Agentic Personalisation of Cross-Channel Marketing Experiences","created":"2025-06-19","cited_by_count":3,"area":"agents"},{"id":"2507.00518","title":"Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2601.10583","title":"Combinatorial Optimization Augmented Machine Learning","created":"2026-01-15","cited_by_count":3,"area":"deeprl"},{"id":"2107.01677","title":"Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics","created":"2021-07-04","cited_by_count":2,"area":null},{"id":"2107.04457","title":"Aligning an optical interferometer with beam divergence control and continuous action space","created":"2021-07-09","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":"2203.00636","title":"Distributional Reinforcement Learning for Scheduling of Chemical Production Processes","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2203.03227","title":"Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimization","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2210.03053","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2211.13257","title":"Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2401.09034","title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2405.15031","title":"Amortized nonmyopic active search via deep imitation learning","created":"2024-05-23","cited_by_count":2,"area":"offlinerl"},{"id":"2406.14169","title":"Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.00567","title":"A Contextual Combinatorial Bandit Approach to Negotiation","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2505.07274","title":"Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2603.26775","title":"Learning to Select Visual In-Context Demonstrations","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"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":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2205.12905","title":"Analytics of Business Time Series Using Machine Learning and Bayesian Inference","created":"2022-05-25","cited_by_count":1,"area":null}],"next_cursor":"100"}