├── README.md └── slides ├── All Lectures.pdf ├── Lecture 1 - introduction.pdf ├── Lecture 10- Approximate Dynamic Programming.pdf ├── Lecture 11- Off-policy and multi-step.pdf ├── Lecture 12- Deep RL 1 .pdf ├── Lecture 13 - Deep RL 2.pdf ├── Lecture 2- Exploration and control_slides.pdf ├── Lecture 3 - MDPs and Dynamic Programming.pdf ├── Lecture 4 - Theoretical Fundamentals of DP Algorithms.pdf ├── Lecture 5 - ModelFreePrediction.pdf ├── Lecture 6 - Model-free control.pdf ├── Lecture 7- Function approximation in reinforcement learning .pdf ├── Lecture 8 - Model Based Reinforcement Learning.pdf └── Lecture 9- Policy gradients and actor critics.pdf /README.md: -------------------------------------------------------------------------------- 1 | # Deepmind x UCL | Reinforcement Learning Course | 2021 2 | this repo contains all of the lecture slides for Deepmind x UCL RL course taught in 2021. 3 | 4 | - presenters: Hado van Hasselt, Diana Borsa, Matteo Hessel 5 | 6 | - [youtube playlist](https://dpmd.ai/DeepMindxUCL21) 7 | 8 | - all slides available as a single pdf file: [All Lectures](<./slides/All Lectures.pdf>) 9 | 10 | ## Slides 11 | 1. [Lecture 1 - introduction](<./slides/Lecture 1 - introduction.pdf>) 12 | 2. [Lecture 2- Exploration and control_slides](<./slides/Lecture 2- Exploration and control_slides.pdf>) 13 | 3. [Lecture 3 - MDPs and Dynamic Programming](<./slides/Lecture 3 - MDPs and Dynamic Programming.pdf>) 14 | 4. [Lecture 4 - Theoretical Fundamentals of DP Algorithms](<./slides/Lecture 4 - Theoretical Fundamentals of DP Algorithms.pdf>) 15 | 5. [Lecture 5 - ModelFreePrediction](<./slides/Lecture 5 - ModelFreePrediction.pdf>) 16 | 6. [Lecture 6 - Model-free control](<./slides/Lecture 6 - Model-free control.pdf>) 17 | 7. [Lecture 7- Function approximation in reinforcement learning ](<./slides/Lecture 7- Function approximation in reinforcement learning .pdf>) 18 | 8. [Lecture 8 - Model Based Reinforcement Learning](<./slides/Lecture 8 - Model Based Reinforcement Learning.pdf>) 19 | 9. [Lecture 9- Policy gradients and actor critics](<./slides/Lecture 9- Policy gradients and actor critics.pdf>) 20 | 10. [Lecture 10- Approximate Dynamic Programming](<./slides/Lecture 10- Approximate Dynamic Programming.pdf>) 21 | 11. [Lecture 11- Off-policy and multi-step](<./slides/Lecture 11- Off-policy and multi-step.pdf>) 22 | 12. [Lecture 12- Deep RL 1 ](<./slides/Lecture 12- Deep RL 1 .pdf>) 23 | 13. [Lecture 13 - Deep RL 2](<./slides/Lecture 13 - Deep RL 2.pdf>) 24 | -------------------------------------------------------------------------------- /slides/All Lectures.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/All Lectures.pdf -------------------------------------------------------------------------------- /slides/Lecture 1 - introduction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 1 - introduction.pdf -------------------------------------------------------------------------------- /slides/Lecture 10- Approximate Dynamic Programming.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 10- Approximate Dynamic Programming.pdf -------------------------------------------------------------------------------- /slides/Lecture 11- Off-policy and multi-step.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 11- Off-policy and multi-step.pdf -------------------------------------------------------------------------------- /slides/Lecture 12- Deep RL 1 .pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 12- Deep RL 1 .pdf -------------------------------------------------------------------------------- /slides/Lecture 13 - Deep RL 2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 13 - Deep RL 2.pdf -------------------------------------------------------------------------------- /slides/Lecture 2- Exploration and control_slides.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 2- Exploration and control_slides.pdf -------------------------------------------------------------------------------- /slides/Lecture 3 - MDPs and Dynamic Programming.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 3 - MDPs and Dynamic Programming.pdf -------------------------------------------------------------------------------- /slides/Lecture 4 - Theoretical Fundamentals of DP Algorithms.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 4 - Theoretical Fundamentals of DP Algorithms.pdf -------------------------------------------------------------------------------- /slides/Lecture 5 - ModelFreePrediction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 5 - ModelFreePrediction.pdf -------------------------------------------------------------------------------- /slides/Lecture 6 - Model-free control.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 6 - Model-free control.pdf -------------------------------------------------------------------------------- /slides/Lecture 7- Function approximation in reinforcement learning .pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 7- Function approximation in reinforcement learning .pdf -------------------------------------------------------------------------------- /slides/Lecture 8 - Model Based Reinforcement Learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 8 - Model Based Reinforcement Learning.pdf -------------------------------------------------------------------------------- /slides/Lecture 9- Policy gradients and actor critics.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yjavaherian/deepmind-x-ucl-rl/41cfe60b709bfded647374942e56715ae14e81da/slides/Lecture 9- Policy gradients and actor critics.pdf --------------------------------------------------------------------------------