{"total":66,"rows":[{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2207.05006","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","created":"2022-07-11","cited_by_count":59,"area":null},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2108.11204","title":"Subgoal Search For Complex Reasoning Tasks","created":"2021-08-25","cited_by_count":21,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2103.11505","title":"Policy-Guided Heuristic Search with Guarantees","created":"2021-03-21","cited_by_count":20,"area":null},{"id":"2107.08170","title":"Megaverse: Simulating Embodied Agents at One Million Experiences per Second","created":"2021-07-17","cited_by_count":20,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2206.00702","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","created":"2022-06-01","cited_by_count":12,"area":null},{"id":"2306.07276","title":"Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving","created":"2023-06-12","cited_by_count":9,"area":"driving"},{"id":"2410.07765","title":"GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2305.16945","title":"Levin Tree Search with Context Models","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2206.03674","title":"Integrating Symmetry into Differentiable Planning with Steerable Convolutions","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2210.13542","title":"Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2504.06048","title":"Trust-Region Twisted Policy Improvement","created":"2025-04-08","cited_by_count":6,"area":"deeprl"},{"id":"2506.17124","title":"When Can Model-Free Reinforcement Learning be Enough for Thinking?","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2402.07963","title":"SPO: Sequential Monte Carlo Policy Optimisation","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2105.01904","title":"Solving Sokoban with forward-backward reinforcement learning","created":"2021-05-05","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2410.22459","title":"Predicting Future Actions of Reinforcement Learning Agents","created":"2024-10-29","cited_by_count":4,"area":"deeprl"},{"id":"2505.17323","title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2510.21995","title":"Is Temporal Difference Learning the Gold Standard for Stitching in RL?","created":"2025-10-24","cited_by_count":4,"area":"deeprl"},{"id":"2206.14298","title":"Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2301.10289","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","created":"2023-01-24","cited_by_count":3,"area":null},{"id":"2302.04798","title":"Equivariant MuZero","created":"2023-02-09","cited_by_count":3,"area":"wm"},{"id":"2602.05999","title":"On the Role of Computation in Reinforcement Learning","created":"2026-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2604.18839","title":"One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2202.01461","title":"ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2209.05206","title":"A Differentiable Loss Function for Learning Heuristics in A*","created":"2022-09-12","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2105.11702","title":"Transfer Learning and Curriculum Learning in Sokoban","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2109.05022","title":"Potential-based Reward Shaping in Sokoban","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2310.11614","title":"Learning a Hierarchical Planner from Humans in Multiple Generations","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2401.11660","title":"Differentiable Tree Search Network","created":"2024-01-22","cited_by_count":1,"area":"wm"},{"id":"2407.09985","title":"A Training Data Recipe to Accelerate A* Search with Language Models","created":"2024-07-13","cited_by_count":1,"area":"lr"},{"id":"2504.03940","title":"Analysis of Robustness of a Large Game Corpus","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.04366","title":"Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks","created":"2025-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2505.07911","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","created":"2025-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2506.07255","title":"Subgoal-Guided Policy Heuristic Search with Learned Subgoals","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2607.18589","title":"Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States","created":"2026-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2608.15958","title":"Solvable Sokoban Without a Solver via Diffusion","created":"2026-08-16","cited_by_count":1,"area":"diffusion"},{"id":"2609.12531","title":"Temporal Recurrence Favors Fewer Layers","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2106.10075","title":"Learning to Plan via a Multi-Step Policy Regression Method","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2406.08687","title":"AlphaZeroES: Direct score maximization outperforms planning loss minimization","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2503.19815","title":"Thinking agents for zero-shot generalization to qualitatively novel tasks","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2507.05465","title":"2048: Reinforcement Learning in a Delayed Reward Environment","created":"2025-07-07","cited_by_count":0,"area":"deeprl"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.30664","title":"Structure-Induced Information for Rerooting Levin Tree Search","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.31106","title":"What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning","created":"2026-06-30","cited_by_count":0,"area":"driving"},{"id":"2607.29577","title":"DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.37432","title":"Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.16992","title":"Generative Models as Adaptive Trust Regions for Discrete Bayesian Optimisation","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17391","title":"Learning to Play: Reinforcement Learning and Games","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}