Deep Mind : video
09  septembre     14h07
2021 DeepMind x UCL RL Lecture Series - Introduction to Reinforcement Learning [1 13]
   Research Scientist Hado van Hasselt introduces the reinforcement learning course and explains how reinforcement learning relates to AI. Slides: https: dpmd.ai introslides Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h07
2021 DeepMind x UCL RL Lecture Series - Exploration & Control [2 13]
   Research Scientist Hado van Hasselt looks at why it’s important for learning agents to balance exploring and exploiting acquired knowledge at the same time. Slides: https: dpmd.ai explorationcontrol Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h07
2021 DeepMind x UCL RL Lecture Series - MDPs and Dynamic Programming [3 13]
   Research Scientist Diana Borsa explains how to solve MDPs with dynamic programming to extract accurate predictions and good control policies. Slides: https: dpmd.ai MDPs Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Theoretical Fund. of Dynamic Programming Algorithms [4 13]
   Research Scientist Diana Borsa explores dynamic programming algorithms as contraction mappings, looking at when and how they converge to the right solutions. Slides: https: dpmd.ai dynamicprogramming Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Model-free Prediction [5 13]
   Research Scientist Hado van Hasselt takes a closer look at model-free prediction and its relation to Monte Carlo and temporal difference algorithms. Slides: https: dpmd.ai modelfreeprediction Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Model-free Control [6 13]
   Research Scientist Hado van Hasselt covers prediction algorithms for policy improvement, leading to algorithms that can learn good behaviour policies from sampled experience. Slides: https: dpmd.ai modelfreecontrol Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Function Approximation [7 13]
   Research Scientist Hado van Hasselt explains how to combine deep learning with reinforcement learning for "deep reinforcement learning". Slides: https: dpmd.ai functionapproximation Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Planning & models [8 13]
   Research Engineer Matteo Hessel explains how to learn and use models, including algorithms like Dyna and Monte-Carlo tree search (MCTS). Slides: https: dpmd.ai planningmodels Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Policy-Gradient and Actor-Critic methods [9 13]
   Research Scientist Hado van Hasselt covers policy algorithms that can learn policies directly and actor critic algorithms that combine value predictions for more efficient learning. Slides: https: dpmd.ai policygradient Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Approximate Dynamic Programming [10 13]
   Research Scientist Diana Borsa introduces approximate dynamic programming, exploring what we can say theoretically about the performance of approximate algorithms. Slides: https: dpmd.ai approximatedynamic Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Multi-step & Off Policy [11 13]
   Research Scientist Hado van Hasselt discusses multi-step and off policy algorithms, including various techniques for variance reduction. Slides: https: dpmd.ai offpolicy Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #1 [12 13]
   Research Engineer Matteo Hessel talks practical considerations and algorithms for deep reinforcement learning, including how to implement them using auto-differentiation (i.e Jax). Slides: https: dpmd.ai deeprl1 Full video lecture series: https: dpmd.ai DeepMindxUCL21
    14h06
2021 DeepMind x UCL RL Lecture Series - Deep Reinforcement Learning #2 [13 13]
   Research Engineer Matteo Hessel covers general value functions, GVFs as auxiliary tasks, and explains how to deal with scaling issues in algorithms. Slides: https: dpmd.ai deeprl2 Full video lecture series: https: dpmd.ai DeepMindxUCL21
27  juillet     14h11
Open-Ended Learning Leads to Generally Capable Agents Results Showreel
   This is the accompanying video for the paper "Open-Ended Learning Leads to Generally Capable Agents" (DeepMind 2021). All results shown are with the same agent and on hand-authored probe tasks that were held out of training. Further reading blog: https: deepmind.com blog article...
22  juillet     15h27
AlphaFold Protein Structure Database
   With EMBL-EBI, we’re proud to launch the AlphaFold Protein Structure Database, which offers the most complete and accurate picture of the human proteome, doubling humanity’s accumulated knowledge of high-accuracy human protein structures - for free. Try it today: dpmd.ai alphafolddb