Online Room B | Evening July 25 19:00-23:00
Session 1
Chair: Yaozeng Huang
Online Room B
Paper 262
19:00-19:15
Reinforcement Learning
Efficient Solution for Collaborative Dynamic Optimization of Maintenance-Scheduling in EMU Depots Based on Hierarchical Reinforcement Learning
Paper 299
19:15-19:30
Reinforcement Learning
Proactive Caching Strategy for Heterogeneous Industrial Edge Networks: A Deep Reinforcement Learning Approach Based on Cognitive Entropy-Driven Attention Mechanism
Paper 546
19:30-19:45
Reinforcement Learning
Online Locality-Aware Conditional Sequence Modeling
Paper 2436
19:45-20:00
Reinforcement Learning
Attention-Based Multi-Agent Reinforcement Learning with Dual Experience Replay Buffers
Paper 3089
20:00-20:15
Reinforcement Learning
Policy Extraction-Based Adversarial Attack in Multi-Agent Reinforcement Learning
Paper 3586
20:15-20:30
Reinforcement Learning
A Hypergraph network dismantling model based on bipartite graph perspective and reinforcement learning
Paper 4190
20:30-20:45
Reinforcement Learning
Subgoal-Induced Reinforcement Learning for Cross-Scene Generalization
Paper 4513
20:45-21:00
Reinforcement Learning
Transformer and Hypernetwork Enhanced Multi-Agent Reinforcement Learning for Multi-Depot Vehicle Routing
Paper 4561
21:00-21:15
Reinforcement Learning
AdaInertia: Dynamic Tool Usage Inertia Control via Deep Q-Learning for Efficient LLM Agent Reasoning
Paper 4810
21:15-21:30
Reinforcement Learning
Heterogeneous Graph-Enhanced MADDPG for UAV Swarm Formation Control
Paper 4815
21:30-21:45
Reinforcement Learning
SafeRecovery: A Safety-Recovery Benchmark with Four-Axis Evaluation for Quadruped Locomotion
Session 2
Chair: Md Rakib Hossain
Online Room B
Paper 5096
21:45-22:00
Reinforcement Learning
Task-driven State Representation for Long-horizon World Model
Paper 5244
22:00-22:15
Reinforcement Learning
Transferring FX Features and WDLP Heads to Accelerate AlphaZero for Gomoku