{"total":143,"rows":[{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2101.11665","title":"On Statistical Bias In Active Learning: How and When To Fix It","created":"2021-01-27","cited_by_count":75,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2306.01711","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2208.07591","title":"Uncertainty-guided Source-free Domain Adaptation","created":"2022-08-16","cited_by_count":46,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2203.03048","title":"Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors","created":"2022-03-06","cited_by_count":39,"area":null},{"id":"2107.14226","title":"Learning more skills through optimistic exploration","created":"2021-07-29","cited_by_count":38,"area":null},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2302.06604","title":"ALAN: Autonomously Exploring Robotic Agents in the Real World","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2211.11865","title":"Bayesian Learning for Neural Networks: an algorithmic survey","created":"2022-11-21","cited_by_count":23,"area":null},{"id":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2107.06068","title":"Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2206.03633","title":"Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping","created":"2022-06-08","cited_by_count":19,"area":null},{"id":"2210.04994","title":"Sampling-based inference for large linear models, with application to linearised Laplace","created":"2022-10-10","cited_by_count":18,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2207.10851","title":"Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction","created":"2022-07-22","cited_by_count":13,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2204.02041","title":"Automating Reinforcement Learning with Example-based Resets","created":"2022-04-05","cited_by_count":12,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2107.11587","title":"Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?","created":"2021-07-24","cited_by_count":11,"area":null},{"id":"2302.05745","title":"Verifying Generalization in Deep Learning","created":"2023-02-11","cited_by_count":11,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2202.13509","title":"Evaluating High-Order Predictive Distributions in Deep Learning","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2301.12579","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2303.06710","title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","created":"2023-03-12","cited_by_count":9,"area":null},{"id":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2403.12729","title":"Posterior Uncertainty Quantification in Neural Networks using Data Augmentation","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2207.01524","title":"Variational Neural Networks","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2411.03932","title":"Improved Regret of Linear Ensemble Sampling","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2102.03719","title":"State-Aware Variational Thompson Sampling for Deep Q-Networks","created":"2021-02-07","cited_by_count":5,"area":null},{"id":"2212.10765","title":"Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2308.12772","title":"Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2503.20394","title":"FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2111.00874","title":"An Uncertainty-Informed Framework for Trustworthy Fault Diagnosis in Safety-Critical Applications","created":"2021-10-08","cited_by_count":4,"area":null},{"id":"2207.07749","title":"Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2302.01051","title":"Randomized prior wavelet neural operator for uncertainty quantification","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2303.04012","title":"Exploration via Epistemic Value Estimation","created":"2023-03-07","cited_by_count":4,"area":null},{"id":"2309.10231","title":"Multi-fidelity climate model parameterization for better generalization and extrapolation","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2310.09766","title":"Pseudo-Bayesian Optimization","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2106.08750","title":"Quasi-Bayesian Dual Instrumental Variable Regression","created":"2021-06-16","cited_by_count":3,"area":null},{"id":"2112.02185","title":"Neural Pseudo-Label Optimism for the Bank Loan Problem","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2203.01004","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2205.08766","title":"Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2205.13528","title":"SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","cited_by_count":3,"area":null},{"id":"2210.01800","title":"Bayesian Q-learning With Imperfect Expert Demonstrations","created":"2022-10-01","cited_by_count":3,"area":null},{"id":"2210.04882","title":"Layer Ensembles","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2210.14488","title":"History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2210.14532","title":"Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2302.05923","title":"Uncertainty-Aware AB3DMOT by Variational 3D Object Detection","created":"2023-02-12","cited_by_count":3,"area":null},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2403.19381","title":"On Uncertainty Quantification for Near-Bayes Optimal Algorithms","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2504.12777","title":"Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2507.11574","title":"Distribution-Free Uncertainty-Aware Virtual Sensing via Conformalized Neural Operators","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2107.04695","title":"L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2202.02405","title":"BAM: Bayes with Adaptive Memory","created":"2022-02-04","cited_by_count":2,"area":null},{"id":"2302.04693","title":"Scaling Goal-based Exploration via Pruning Proto-goals","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2302.07260","title":"Scalable Bayesian optimization with high-dimensional outputs using randomized prior networks","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2308.15550","title":"Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning","created":"2023-08-29","cited_by_count":2,"area":null}],"next_cursor":"100"}