2019

  1. Elastic Weight Consolidation
  2. Variational Inference
  3. MCMC Methods for Posterior Approximation
  4. WiseMove: Investigating Safe Autonomous Driving
  5. Uber's Go Explore

2018

  1. Hindsight Experience Replay
  2. GridDriving: Gym simulator
  3. Indoor Target-driven Visual Navigation
  4. Quantum TD Learning
  5. Proximal Policy Optimization
  6. Safe, Multi Agent RL for Autonomous Driving
  7. Trust Region Policy Optimization
  8. Automated Driving in Uncertain Environments
  9. Deep Deterministic Policy Gradient

2017

  1. Capsule Networks: FashionMNIST
  2. Flappy Bird: UCB, Bootstrapped DQN
  3. Bootstrapped DQN
  4. UCB1, Multi Armed Bandits and Regret
  5. Value functions and the Bellman Loss