Exploration

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration CVPR 2026 Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning ICLR 2025 Entropy-based Exploration Conduction for Multi-step Reasoning ACL 2025 Learning Joint Behaviors with Large Variations AAAI 2025 Nearly Tight Bounds for Exploration in Streaming Multi-Armed Bandits with Known Optimality Gap AAAI 2025 Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning AAAI 2025 Pure Exploration with Feedback Graphs AISTATS 2025 Adaptive Exploration for Data-Efficient General Value Function Evaluations NeurIPS 2024 Beyond Optimism: Exploration With Partially Observable Rewards NeurIPS 2024 Controlled maximal variability along with reliable performance in recurrent neural networks NeurIPS 2024 Exploring Beyond Curiosity Rewards: Language-Driven Exploration in RL ACML 2024 Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning NeurIPS 2024 Harnessing Density Ratios for Online Reinforcement Learning ICLR 2024 How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach NeurIPS 2024 Leveraging Separated World Model for Exploration in Visually Distracted Environments NeurIPS 2024 Optimal Top-Two Method for Best Arm Identification and Fluid Analysis NeurIPS 2024 Population-Based Diverse Exploration for Sparse-Reward Multi-Agent Tasks IJCAI 2024 Preference-based Pure Exploration NeurIPS 2024 QUIS: Question-guided Insights Generation for Automated Exploratory Data Analysis EMNLP 2024 Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus NeurIPS 2024 Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration AAAI 2024 Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks ICLR 2024 Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing AAAI 2024 The Value of Reward Lookahead in Reinforcement Learning NeurIPS 2024 Unlocking the Power of Representations in Long-term Novelty-based Exploration ICLR 2024