Dieqiao Feng

5 papers · 2020–2023 · 3 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 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13)

Venues

NeurIPS (3) ICML (1) IJCAI (1)

Top co-authors

Bart Selman (4) Carla P. Gomes (3) Yuanqi Du (2) Limei Wang (1) Zhi-ming Ma (1) Guifeng Wang (1) Carla Gomes (1) weitao Du (1) Shuiwang Ji (1) Carla P Gomes (1)

Research topics

Reinforcement Learning (4) Artificial Intelligence (3) Deep Learning (3) Machine Learning (3) Core AI (3) Methods (3) Applications (2) Learning Types (2) Optimization & Theory (2) Knowledge & Reasoning (1) Architectures (1) Core Methods (1) Learning Paradigms (1) Reasoning (1)

Keywords

curriculum learning (2) sokoban planning (2) deep reinforcement learning (2) policy learning (1) geometric deep learning (1) best-first search (1) gradient estimation (1) top-k classification (1) deep neural network (1) heavy-tailed distribution (1) equivariant graph neural network (1) policy network (1) value network (1) cross-entropy loss (1) molecular property prediction (1) noisy data (1) ai planning (1) curiosity-driven exploration (1) automated curriculum (1) weighted sampling (1)

Papers

A new perspective on building efficient and expressive 3D equivariant graph neural networks NeurIPS 2023 Weighted Sampling without Replacement for Deep Top-k Classification ICML 2023 Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning NeurIPS 2022 A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances NeurIPS 2020 Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning IJCAI 2020