{"total":10,"rows":[{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2410.02172","title":"Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation","created":"2024-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2605.05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2403.01605","title":"Towards Provable Log Density Policy Gradient","created":"2024-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.01028","title":"A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning","created":"2026-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2609.13044","title":"Robust Policy Optimization via Adversarial Importance Sampling","created":"2026-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2609.28581","title":"Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}