{"total":75,"rows":[{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2206.14262","title":"Supervised Training of Conditional Monge Maps","created":"2022-06-28","cited_by_count":61,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"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":"2109.05490","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","created":"2021-09-12","cited_by_count":35,"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":"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":"2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","created":"2021-03-29","cited_by_count":32,"area":null},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2402.10450","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","created":"2024-02-16","cited_by_count":21,"area":"offlinerl"},{"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":"2402.02171","title":"Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction","created":"2024-02-03","cited_by_count":17,"area":null},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2503.01206","title":"Action Tokenizer Matters in In-Context Imitation Learning","created":"2025-03-03","cited_by_count":14,"area":"offlinerl"},{"id":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"area":null},{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2102.11327","title":"Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":"offlinerl"},{"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":"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":"2403.09976","title":"AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors","created":"2024-03-15","cited_by_count":10,"area":"wm"},{"id":"2102.11329","title":"Action Redundancy in Reinforcement Learning","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2202.06557","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution","created":"2022-02-14","cited_by_count":9,"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":"2106.00897","title":"Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","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":"2103.02957","title":"Toward Robust Long Range Policy Transfer","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2110.03608","title":"How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents","created":"2021-10-07","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":"2210.09566","title":"Simple Emergent Action Representations from Multi-Task Policy Training","created":"2022-10-18","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":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2305.19922","title":"Representation-Driven Reinforcement Learning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2410.15184","title":"Action abstractions for amortized sampling","created":"2024-10-19","cited_by_count":4,"area":"deeprl"},{"id":"2503.01411","title":"Learning Actionable World Models for Industrial Process Control","created":"2025-03-03","cited_by_count":4,"area":"wm"},{"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":"2304.00873","title":"Action Pick-up in Dynamic Action Space Reinforcement Learning","created":"2023-04-03","cited_by_count":3,"area":null},{"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":"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":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","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":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2206.12700","title":"Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation","created":"2022-06-25","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":"2302.11917","title":"Diverse Policy Optimization for Structured Action Space","created":"2023-02-23","cited_by_count":1,"area":"alignment"},{"id":"2505.22531","title":"Training RL Agents for Multi-Objective Network Defense Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.05702","title":"Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2604.03472","title":"Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.15215","title":"A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics","created":"2026-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2105.03041","title":"Utilizing Skipped Frames in Action Repeats via Pseudo-Actions","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2106.02943","title":"Learning Routines for Effective Off-Policy Reinforcement Learning","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2110.10632","title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences","created":"2021-10-20","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":"2406.10538","title":"Addressing Large Action Spaces in 3D Floorplanning via Spatial Generalization","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2501.14543","title":"Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation","created":"2025-01-24","cited_by_count":0,"area":"deeprl"},{"id":"2504.07425","title":"Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games","created":"2025-04-10","cited_by_count":0,"area":"agents"},{"id":"2505.09756","title":"LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2505.14209","title":"Embedded Mean Field Reinforcement Learning for Perimeter-defense Game","created":"2025-05-20","cited_by_count":0,"area":"deeprl"},{"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":"2507.07769","title":"BEAVER: Building Environments with Assessable Variation for Evaluating Multi-Objective Reinforcement Learning","created":"2025-07-10","cited_by_count":0,"area":"deeprl"},{"id":"2602.08616","title":"Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces","created":"2026-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2602.22786","title":"QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.23308","title":"CODA: Coordination via On-Policy Diffusion for Multi-Agent Offline Reinforcement Learning","created":"2026-04-25","cited_by_count":0,"area":"offlinerl"},{"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":"2608.24156","title":"LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes","created":"2026-08-25","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}