WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Paper • 2608.24479 • Published • 142
🤝 Open to Collab
Song Huizhong
bonstoppo
AI & ML interests
Multi-agent System, Embodied AI
Recent Activity
authored a paper 9 days ago
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation authored a paper 9 days ago
Risk-aware Direct Preference Optimization under Nested Risk MeasureOrganizations
None yet