Dongcui Diao

2 papers · 2009–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

AAAI (1) NeurIPS (1)

Top co-authors

Hengshuai Yao (2) Hechang Chen (1) Shalabh Bhatnagar (1) Zhiwei Yang (1) Richard S. Sutton (1) Bei Jiang (1) haiyin piao (1) Yi Chang (1) Zhixiao Sun (1) Csaba Szepesvári (1)

Research topics

Artificial Intelligence (2) Reinforcement Learning (2) Core AI (2) Methods (2) Machine Learning (1) Learning Types (1)

Keywords

policy evaluation (1) policy gradient (1) value function (1) model-based reinforcement learning (1) off-policy learning (1) multi-step planning (1) dyna architecture (1) lambda model (1) proximal policy optimization (1) conservative policy iteration (1) multi-step learning (1) dyna planning (1) soft clipping (1)

Papers

The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure AAAI 2023 Multi-Step Dyna Planning for Policy Evaluation and Control NeurIPS 2009