{"total":11,"rows":[{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2501.12670","title":"Celo: Training Versatile Learned Optimizers on a Compute Diet","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.06355","title":"A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2609.12531","title":"Temporal Recurrence Favors Fewer Layers","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2609.04807","title":"CoLMIN: LLM-based Multi-Decision Path Negotiation for Cooperative Autonomous Driving","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.17007","title":"Mixture of GFlowNets","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}