{"total":24,"rows":[{"id":"2108.06084","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","created":"2021-08-13","cited_by_count":36,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2301.06276","title":"The Role of Baselines in Policy Gradient Optimization","created":"2023-01-16","cited_by_count":25,"area":null},{"id":"2205.14345","title":"Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2104.04192","title":"Reinforced Attention for Few-Shot Learning and Beyond","created":"2021-04-09","cited_by_count":18,"area":null},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2201.01811","title":"CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation","created":"2022-01-05","cited_by_count":10,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2107.12216","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","created":"2021-07-26","cited_by_count":7,"area":null},{"id":"2103.02957","title":"Toward Robust Long Range Policy Transfer","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2307.11685","title":"Towards Generalizable Reinforcement Learning for Trade Execution","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2206.06827","title":"Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2303.12957","title":"Reinforcement Learning with Exogenous States and Rewards","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2201.05819","title":"Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2101.11685","title":"CNN with large memory layers","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2301.13799","title":"Partitioning Distributed Compute Jobs with Reinforcement Learning and Graph Neural Networks","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2302.12403","title":"Plume: A Framework for High Performance Deep RL Network Controllers via Prioritized Trace Sampling","created":"2023-02-24","cited_by_count":0,"area":null},{"id":"2302.13483","title":"CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2604.02927","title":"Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms","created":"2026-04-03","cited_by_count":0,"area":null}],"next_cursor":null}