{"total":41,"rows":[{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2104.03086","title":"Trajectory Prediction with Latent Belief Energy-Based Model","created":"2021-04-07","cited_by_count":60,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2304.02012","title":"EGC: Image Generation and Classification via a Diffusion Energy-Based Model","created":"2023-04-04","cited_by_count":16,"area":null},{"id":"2301.05579","title":"A survey and taxonomy of loss functions in machine learning","created":"2023-01-13","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2105.04184","title":"Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation","created":"2021-05-10","cited_by_count":11,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2106.07832","title":"Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent","created":"2021-06-15","cited_by_count":10,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2312.01811","title":"Energy-based Potential Games for Joint Motion Forecasting and Control","created":"2023-12-04","cited_by_count":9,"area":null},{"id":"2306.14902","title":"Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2409.08212","title":"Adaptive Language-Guided Abstraction from Contrastive Explanations","created":"2024-09-12","cited_by_count":8,"area":null},{"id":"2102.11905","title":"Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2202.10057","title":"CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories","created":"2022-02-21","cited_by_count":6,"area":null},{"id":"2110.05286","title":"Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2210.05845","title":"Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2308.16539","title":"On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2311.08530","title":"SceneScore: Learning a Cost Function for Object Arrangement","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2310.19831","title":"Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2303.11649","title":"CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2603.26695","title":"Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.01169","title":"Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2309.01784","title":"INTAGS: Interactive Agent-Guided Simulation","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2103.08475","title":"Deep Consensus Learning","created":"2021-03-15","cited_by_count":0,"area":null},{"id":"2205.09433","title":"CAMEO: Curiosity Augmented Metropolis for Exploratory Optimal Policies","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2301.07421","title":"DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2404.13218","title":"On the Temperature of Machine Learning Systems","created":"2024-04-19","cited_by_count":0,"area":null},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2409.18982","title":"Aligning Robot Navigation Behaviors with Human Intentions and Preferences","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2509.17205","title":"Conditional Policy Generator for Dynamic Constraint Satisfaction and Optimization","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2605.03660","title":"Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning","created":"2026-05-05","cited_by_count":0,"area":null}],"next_cursor":null}