{"total":16,"rows":[{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"id":"2601.22475","title":"Continual Policy Consolidation for Lifelong Robot Learning","created":"2026-01-30","cited_by_count":3,"area":"deeprl"},{"id":"2602.12636","title":"Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL","created":"2026-02-13","cited_by_count":2,"area":"deeprl"},{"id":"2605.19919","title":"Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning","created":"2026-05-19","cited_by_count":2,"area":"deeprl"},{"id":"2510.08442","title":"Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning","created":"2025-10-09","cited_by_count":1,"area":"deeprl"},{"id":"2607.16534","title":"Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning","created":"2026-07-17","cited_by_count":1,"area":"deeprl"},{"id":"2512.14057","title":"Context Representation via Action-Free Transformer encoder-decoder for Meta Reinforcement Learning","created":"2025-12-16","cited_by_count":0,"area":"deeprl"},{"id":"2605.11473","title":"TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.14350","title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","created":"2026-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2605.26012","title":"Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.03335","title":"A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.03382","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.20324","title":"A Model-Driven Approach for Developing Families of Reinforcement Learning Environments","created":"2026-06-18","cited_by_count":0,"area":"deeprl"},{"id":"2607.24996","title":"Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.35333","title":"Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillation","created":"2026-09-28","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}