{"total":57,"rows":[{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"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":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"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":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"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":"2206.10786","title":"Generative Pretraining for Black-Box Optimization","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","cited_by_count":13,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2507.07995","title":"Single-pass Adaptive Image Tokenization for Minimum Program Search","created":"2025-07-10","cited_by_count":12,"area":null},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2205.06595","title":"Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets","created":"2022-05-13","cited_by_count":10,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2101.04750","title":"Linear Representation Meta-Reinforcement Learning for Instant Adaptation","created":"2021-01-12","cited_by_count":9,"area":null},{"id":"2204.05027","title":"Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning","created":"2022-04-11","cited_by_count":9,"area":null},{"id":"2207.01570","title":"Goal-Conditioned Generators of Deep Policies","created":"2022-07-04","cited_by_count":9,"area":null},{"id":"2412.10410","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2211.06407","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2303.07519","title":"Architext: Language-Driven Generative Architecture Design","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2601.18175","title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2202.12742","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2402.17501","title":"Intensive Care as One Big Sequence Modeling Problem","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2404.07351","title":"A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2510.09596","title":"BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2603.13733","title":"Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2405.06063","title":"A Minimalist Prompt for Zero-Shot Policy Learning","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2303.08909","title":"Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning","created":"2023-03-15","cited_by_count":1,"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":"2412.08565","title":"GenPlan: Generative Sequence Models as Adaptive Planners","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2502.09854","title":"Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2606.24231","title":"FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.32027","title":"Freeform Preference Learning for Robotic Manipulation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2309.16291","title":"Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2310.08100","title":"Generative Intrinsic Optimization: Intrinsic Control with Model Learning","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2610.15515","title":"Semantically Steerable Image Tokenization","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}