{"total":69,"rows":[{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248,"area":null},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2106.07156","title":"Temporal Predictive Coding For Model-Based Planning In Latent Space","created":"2021-06-14","cited_by_count":55,"area":null},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2103.15819","title":"Augmenting Automated Game Testing with Deep Reinforcement Learning","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27,"area":null},{"id":"2110.12628","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21,"area":null},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2111.11107","title":"Branching Time Active Inference: the theory and its generality","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2302.12003","title":"Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions","created":"2023-02-12","cited_by_count":14,"area":null},{"id":"2212.02721","title":"A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networks","created":"2022-12-06","cited_by_count":12,"area":null},{"id":"2105.01006","title":"Robotic Surgery With Lean Reinforcement Learning","created":"2021-05-03","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2303.02160","title":"Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2108.13696","title":"Phy-Q as a measure for physical reasoning intelligence","created":"2021-08-31","cited_by_count":10,"area":null},{"id":"2111.11276","title":"Branching Time Active Inference: empirical study and complexity class analysis","created":"2021-11-22","cited_by_count":9,"area":null},{"id":"2203.02583","title":"Online Learning of Reusable Abstract Models for Object Goal Navigation","created":"2022-03-04","cited_by_count":9,"area":null},{"id":"2306.01598","title":"Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2105.06228","title":"SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2403.05468","title":"Will GPT-4 Run DOOM?","created":"2024-03-08","cited_by_count":6,"area":null},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2303.01618","title":"Deconstructing deep active inference","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2309.01194","title":"A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects","created":"2023-09-03","cited_by_count":5,"area":null},{"id":"2106.01741","title":"Lifetime policy reuse and the importance of task capacity","created":"2021-06-03","cited_by_count":4,"area":null},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2312.07025","title":"Noise Distribution Decomposition based Multi-Agent Distributional Reinforcement Learning","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2408.13934","title":"Learning to Move Like Professional Counter-Strike Players","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2105.03172","title":"Reward prediction for representation learning and reward shaping","created":"2021-05-07","cited_by_count":3,"area":null},{"id":"2107.00703","title":"Distilling Reinforcement Learning Tricks for Video Games","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2111.06449","title":"Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2206.14198","title":"Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2306.01066","title":"Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2406.08404","title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2504.13478","title":"Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2201.00411","title":"The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents","created":"2022-01-02","cited_by_count":2,"area":null},{"id":"2203.01465","title":"Deep Q-network using reservoir computing with multi-layered readout","created":"2022-03-03","cited_by_count":2,"area":null},{"id":"2306.12314","title":"Introspective Action Advising for Interpretable Transfer Learning","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2508.08382","title":"UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2604.07385","title":"Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2104.11798","title":"Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker","created":"2021-04-23","cited_by_count":1,"area":null},{"id":"2110.09817","title":"State-based Episodic Memory for Multi-Agent Reinforcement Learning","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2210.09026","title":"WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2310.08331","title":"Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2312.14824","title":"An investigation of belief-free DRL and MCTS for inspection and maintenance planning","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2102.11762","title":"School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2103.16732","title":"Simultaneous Navigation and Construction Benchmarking Environments","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2109.00927","title":"Autonomous Curiosity for Real-Time Training Onboard Robotic Agents","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2208.00525","title":"Learning to generate Reliable Broadcast Algorithms","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2208.04568","title":"The Impact of Data Corruption on Named Entity Recognition for Low-resourced Languages","created":"2022-08-09","cited_by_count":0,"area":null},{"id":"2209.04999","title":"Multi-Step First: A Lightweight Deep Reinforcement Learning Strategy for Robust Continuous Control with Partial Observability","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2309.02869","title":"On Reducing Undesirable Behavior in Deep Reinforcement Learning Models","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2312.12904","title":"PGN: A perturbation generation network against deep reinforcement learning","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2601.22369","title":"Learning Provably Correct Distributed Protocols Without Human Knowledge","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.18981","title":"How Far Can We Go with Pixels Alone? A Pilot Study on Screen-Only Navigation in Commercial 3D ARPGs","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.06608","title":"Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark","created":"2026-02-19","cited_by_count":0,"area":null}],"next_cursor":null}