• OpenEdu MB-RL: MCTS, AlphaZero, MuZero

  • Copy of Title DRLRG

  • Title DRLRG

  • Copy of К анонсу Practical-RL ШАД

  • К анонсу Practical-RL ШАД

  • CEM

  • Copy of FTIAD RL #5 Policy Gradient

  • RL #2 Dynamic Programming

  • FTIAD RL #1 Intro, BC, CEM

  • AIRI report Interview

  • Exploration vs. Exploitation

  • deck

  • Intro in RL for Sber (Sk)

  • Bespoke shoe making (Russian)

  • Bespoke shoe making

  • MB-RL: LQR, iLQR, DDP

  • PI and VI (OZON)

  • Bayesian Exploration for Petroleum Industry

  • deck

  • Cross Entropy Method (OZON)

  • Bandit Algorithms

  • exam_presentation

  • Serbia_meeting_8_12_20

  • MB-RL: MCTS, AlphaZero, MuZero

  • Imitation and Inverse RL

  • Annual Review

  • Distributional RL

  • Micro-Learning Temirchev Pavel

  • Metamodelling colossal plans

  • Adv RL: RL as probabilistic inference

  • Intro to RL, lecture 2: Q-learning (ISP)

  • Intro to RL, lecture 1: Tabular RL (ISP)

  • Decomposition of Uncertainty in Bayesian Deep Learning

  • Dynamic Mode Decomposition

  • Intro to RL, part 1 (pizza-seminar)

  • (bayessem) Reinforcement Learning as Probabilistic Inference

  • (datafest) Reinforcement Learning as Probabilistic Inference

  • Model-Ensemble Trust Region Policy Optimization

  • Approximate Linear Programming for Markov Decision Processes

  • Curiosity-driven Exploration by Self-Supervised Prediction