Jun Zhu

Latest

• DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
• DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
• VMAPD: Generate Diverse Solutions for Multi-Agent Games with Recurrent Trajectory Discriminators
• Off-Policy Training for Truncated TD ($łambda$) Boosted Soft Actor-Critic
• Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization
• TiKick: towards playing multi-agent football full games from single-agent demonstrations
• Svqn: Sequential variational soft q-learning networks
• Combo-action: Training agent for fps game with auxiliary tasks
• Dropout training for SVMs with data augmentation