{"total":90,"rows":[{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"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":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2302.05817","title":"Level Generation Through Large Language Models","created":"2023-02-11","cited_by_count":68,"area":null},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","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":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2203.04098","title":"COLA: Consistent Learning with Opponent-Learning Awareness","created":"2022-03-08","cited_by_count":38,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","cited_by_count":26,"area":null},{"id":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25,"area":null},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23,"area":null},{"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":"2103.04693","title":"Unsupervised Object-Based Transition Models for 3D Partially Observable Environments","created":"2021-03-08","cited_by_count":20,"area":null},{"id":"2103.11505","title":"Policy-Guided Heuristic Search with Guarantees","created":"2021-03-21","cited_by_count":20,"area":null},{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","cited_by_count":19,"area":null},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"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":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2103.08255","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","created":"2021-03-15","cited_by_count":16,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2201.09765","title":"Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning","created":"2022-01-24","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":"2110.00898","title":"A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2112.11490","title":"Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding","created":"2021-12-21","cited_by_count":9,"area":null},{"id":"2208.07123","title":"Online 3D Bin Packing Reinforcement Learning Solution with Buffer","created":"2022-08-15","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2212.01939","title":"Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance","created":"2022-12-04","cited_by_count":7,"area":null},{"id":"2307.01995","title":"Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2105.05145","title":"Visual Perspective Taking for Opponent Behavior Modeling","created":"2021-05-11","cited_by_count":6,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2112.01918","title":"Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning","created":"2021-12-03","cited_by_count":6,"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":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","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":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2106.08272","title":"Deep Reinforcement Learning for Conservation Decisions","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2105.01904","title":"Solving Sokoban with forward-backward reinforcement learning","created":"2021-05-05","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2104.03638","title":"Spatial Imagination With Semantic Cognition for Mobile Robots","created":"2021-04-08","cited_by_count":3,"area":null},{"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":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2103.00446","title":"Learning for Visual Navigation by Imagining the Success","created":"2021-02-28","cited_by_count":2,"area":null},{"id":"2104.08196","title":"Towards Standardising Reinforcement Learning Approaches for Production Scheduling Problems","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"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":"2209.02010","title":"On the Origins of Self-Modeling","created":"2022-09-05","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":"2304.14698","title":"X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2606.26463","title":"Finding the Time to Think: Learning Planning Budgets in Real-Time RL","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2102.05249","title":"Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms","created":"2021-02-10","cited_by_count":1,"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":"2111.08010","title":"Modular Networks Prevent Catastrophic Interference in Model-Based Multi-Task Reinforcement Learning","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2112.05218","title":"Learning Generalizable Behavior via Visual Rewrite Rules","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2201.05464","title":"Bayesian sense of time in biological and artificial brains","created":"2022-01-14","cited_by_count":1,"area":null},{"id":"2209.12029","title":"Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2212.07397","title":"Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2302.05448","title":"The Construction of Reality in an AI: A Review","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2306.04440","title":"Dual policy as self-model for planning","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2405.01114","title":"Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modeling","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2512.21201","title":"Schr\\\"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2104.06339","title":"Deep imagination is a close to optimal policy for planning in large decision trees under limited resources","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2104.08543","title":"Planning with Expectation Models for Control","created":"2021-04-17","cited_by_count":0,"area":null},{"id":"2109.13463","title":"Deep Reinforcement Learning with Adjustments","created":"2021-09-28","cited_by_count":0,"area":null},{"id":"2110.14157","title":"Dream to Explore: Adaptive Simulations for Autonomous Systems","created":"2021-10-27","cited_by_count":0,"area":null},{"id":"2112.15034","title":"Self Reward Design with Fine-grained Interpretability","created":"2021-12-30","cited_by_count":0,"area":null},{"id":"2211.03281","title":"Reward-Predictive Clustering","created":"2022-11-07","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":"2312.08724","title":"Personalized Path Recourse for Reinforcement Learning Agents","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2403.03172","title":"Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination","created":"2024-03-05","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":"2507.20312","title":"A Comparative Study of OpenMP Scheduling Algorithm Selection Strategies","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2510.20636","title":"Fluidity Index: Next-Generation Super-intelligence Benchmarks","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2602.12520","title":"Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings","created":"2026-02-13","cited_by_count":0,"area":null}],"next_cursor":null}