Department of Computing Science, University of Alberta.
Canada, T6G 2E8.
Email: cgao3 AT ualberta.ca
I am a PhD student at the Department of Computing Science, co-supervised by Prof. Martin Mueller and Prof. Ryan Hayward.
I received my M.S. degree in 2015 from the Department of Computer Science and Technology from University of Science and Technology of China, where I worked at USTC-Birmingam Joint Research Institute in Intelligent Computation and Its Applications.
I have a wide interest in various aspects of Artificial Intelligence and Operations Research.
Programming Language: C++, Java, C, Python, Linux Shell, TensorFlow, PyTorch.
- Chao Gao, Bilal Kartal, Pablo Hernandez Leal and Matthew Taylor. On Hard Exploration for Reinforcement Learning: A Case Study in Pommerman, AIIDE 2019 (ORAL 25% acceptance rate).
- Chao Gao, Siqi Yan, Ryan Hayward, Martin Mueller. A transferable neural network for Hex CG2018. At 21st Computer Olympiad, our program MoHex3HNN based on three-head net and transfer learning (128 filters per layer, 10 residual blocks, iteratively trained on ~0.4 million self-play generated games) won 11x11 and 13x13 Hex tournaments against DeepEzo from Japan. DeepEzo was trained using minimax search based RL for several millions of games. Note that in comparison to MoHex3HNN and DeepEzo, previous champion program MoHex 2.0 is now a weak baseline. See report Hex 2018: MoHex3HNN over DeepEzo
- Chao Gao, Martin Mueller, Ryan Hayward. Three-Head Neural Network Architecture for Monte Carlo Tree Search. IJCAI-ECAI 2018.
- Chao Gao, Martin Mueller, Ryan Hayward. Adversarial Policy Gradient for Alterating Markov Games. Sixth International Conference on Learning Representations (ICLR 2018), Workshop track, 2018.
- Chao Gao, Ryan Hayward, Martin Mueller. Move Prediction using Deep Convolutional Neural Networks in Hex. IEEE Transaction on Games, 2017.
- Chao Gao, Ryan Hayward, Martin Mueller. Focused depth-first proof number search using convolutional neural networks for the game of Hex. Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI-2017).
- Xuebin Qin, Vincent Zhang, Chenyang Huang, Chao Gao, Masood Dehghan, Martin Jagersand. BASNet: Boundary Aware Salient Object Detection. CVPR 2019. source code.
Chao Gao, Guanzhou Lu, Xin Yao, Jinlong Li. A Pseudo-gap Enumeration Approach for the Multidimensional Multiple-choice Knapsack Problem. European Journal of Operational Research, 260.1 (2017): 1-11. author’s version, source code.
Chao Gao, Xin Yao, Thomas Weise, Jinlong Li. An efficient local search heuristic with row-weighting for the unicost set covering problem. European Journal of Operational Research, 246.3 (2015): 750-761. author’s version, source code.