Publications

Filter by type:
(2019). Primal-dual Sub-gradient Approximation based Policy Gradient Search. Submitted for review to the journal “IEEE Transaction on Neural Networks and Learning Systems”.

Code

(2019). Proximal Evolutionary Strategies: Achieving State-of-the-art Deep Reinforcement Learning through Evolutionary Policy Optimization. Submitted for review to the journal “IEEE Transaction on Evolutionary Computation”.

Code

(2018). An Adaptive Clipping Approach for Proximal Policy Optimization. arxiv preprint.

PDF DOI

(2017). Evolving Transferable Artificial Neural Networks for Gameplay Tasks via NEAT with Phased Searching. Australian AI 2017.

PDF DOI

(2017). A Sandpile Model for Reliable Actor-Critic Reinforcement Learning. IJCNN.

PDF DOI

(2017). Automated State Feature Learning for Actor-Critic Reinforcement Learning through NEAT. GECCO.

PDF DOI

(2016). Generalized Compatible Function Approximation for Policy Gradient Search. ICONIP.

PDF DOI

(2015). A Federated Online Network Traffic Analysis Engine for Cybersecurity.. IJCNN.

PDF DOI

(2013). Chunk incremental IDR/QR LDA learning. IJCNN.

PDF DOI

(2012). Exploring Crude Oil Impacts to Oil Stocks through Graphical Computational Correlation Analysis. ICONIP.

PDF DOI