Pinned Loading

1. Flatland-DMM Flatland-DMM Public

   Multi-Agent Reinforcement Learning challenge on trains re-scheduling problem (RSP) organized by the AIcrowd platform in collaboration with the Swiss Federal Railways.

   Python 5

2. MetaRL-RL2 MetaRL-RL2 Public

   Meta Reinforcement Learning (RL²) techniques applied to Actor Critic (A2C,A3C) methods to develop agents capable of acting in multiple environment distributions.

   Python

3. VLSI VLSI Public

   Project for modelling and solving the VLSI (Very Large Scale Integration) combinatorial decision problem with CP, SAT, SMT and ILP.

   Jupyter Notebook

4. SVM SVM Public

   Implementation of Support Vector Machine algorithm using Lagrange Multipliers method for solving non-linear constrained optimization problems.

   Python 2