Publicly available code from my group, released through github.

Code for Published Papers

  • Training Recurrent Neural Networks Online by Learning Explicit State Variables, with [pdf]. Code from Vincent Liu on [github].

  • Maxmin Q-learning: Controlling the Estimation Bias of Q-learning, with [pdf]. Code from Qinfeng Lan on [github].

  • Meta-Learning Representations for Continual Learning, with [pdf]. Code from Khurram Javed on [github].

  • Importance Resampling for Off-policy Prediction, with [pdf]. Code from Matthew Schlegel on [github].

  • Accelerated Gradient Temporal Difference Learning, with [pdf]. Code from Yangchen Pan on [github].

  • Incremental Truncated LSTD, with [pdf]. Code from Yangchen Pan on [github].

  • Optimal Estimation of Multivariate ARMA Models, with [pdf]. Code from Martha White on [github].

  • Convex Multi-view Subspace Learning, with [pdf]. Code from Martha White on [github].
  • Generalized Optimal Reverse Prediction, with [pdf]. Code from Martha White on [github].

  • Convex Sparse Coding, Subspace Learning, and Semi-Supervised Extensions, with [pdf]. Code from Martha White on [github].