Tensorflow + OpenAI Gym implementation of Deep Q-Network (DQN), Double DQN (DDQN), Dueling Network and Deep Deterministic Policy Gradient (DDPG)

Open-source simulator for autonomous driving research.

Source code for experiments in the papers "Complex Embeddings for Simple Link Prediction" (ICML 2016) and "Knowledge Graph Completion via Complex Tensor Factorization" (JMLR 2017).

A knowledge base completion method which handles temporal metadata