{"total":28,"rows":[{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2306.00249","title":"BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2310.12819","title":"Hybrid Search for Efficient Planning with Completeness Guarantees","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2406.00614","title":"Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2310.02442","title":"GenCO: Generating Diverse Designs with Combinatorial Constraints","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2510.23214","title":"AUPO -- Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2511.15055","title":"Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2302.12636","title":"Streamlining Multimodal Data Fusion in Wireless Communication and Sensor Networks","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2510.24297","title":"Investigating Intra-Abstraction Policies For Non-exact Abstraction Algorithms","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2307.14151","title":"Learning Disentangled Discrete Representations","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2404.13150","title":"Transformer Based Planning in the Observation Space with Applications to Trick Taking Card Games","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2405.09557","title":"Machine Learning in Short-Reach Optical Systems: A Comprehensive Survey","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2606.30940","title":"Motion Planning in Compressed Representation Spaces","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2302.07950","title":"Self-Organising Neural Discrete Representation Learning \\`a la Kohonen","created":"2023-02-15","cited_by_count":0,"area":null},{"id":"2305.13206","title":"Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2506.11511","title":"Task-Driven Discrete Representation Learning","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2510.26346","title":"Discovering State Equivalences in UCT Search Trees By Action Pruning","created":"2025-10-30","cited_by_count":0,"area":null}],"next_cursor":null}