{"total":14,"rows":[{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2408.08677","title":"Neural Reward Machines","created":"2024-08-16","cited_by_count":7,"area":"deeprl"},{"id":"2403.18725","title":"Probabilistic Model Checking of Stochastic Reinforcement Learning Policies","created":"2024-03-27","cited_by_count":5,"area":"deeprl"},{"id":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"id":"2503.04931","title":"Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation","created":"2025-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2410.09686","title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning","created":"2024-10-13","cited_by_count":1,"area":"deeprl"},{"id":"2411.01425","title":"Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning","created":"2024-11-03","cited_by_count":1,"area":"deeprl"},{"id":"2412.19194","title":"Provably Efficient Exploration in Reward Machines with Low Regret","created":"2024-12-26","cited_by_count":1,"area":"deeprl"},{"id":"2509.19017","title":"Fully Learnable Neural Reward Machines","created":"2025-09-23","cited_by_count":1,"area":"deeprl"},{"id":"2602.02532","title":"CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning","created":"2026-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2602.09761","title":"Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization","created":"2026-02-10","cited_by_count":1,"area":"deeprl"},{"id":"2603.07546","title":"COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance","created":"2026-03-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.24740","title":"Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality","created":"2026-05-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}