Reinforcement Learning (RL) is an area of Machine Learning that has recently made large advances and has been publicly visible by reaching and surpassing human skill levels in games like Go and Starcraft. These successes show that RL has the potential to transform many areas of research and industry by automatizing the development of processes that once needed to be engineered explicitly.
In contrast to other machine learning paradigms, which require the presence of (labeled or unlabeled) data, RL considers an agent that takes actions in an environment and learns from resulting feedback. The agent tries to maximize a reward signal that it receives for desirable outcomes, while at the same time trying to explore the world in which it operates to find yet unknown, potentially more rewarding action sequences–a dilemma known as the exploration-exploitation tradeoff. Recent advances in machine learning based on deep learning have made RL methods particularly powerful since they allow for agents with particularly well performing models of the world.
The seminar will start with 6 introductory lectures to RL where we cover the foundations of RL (i.e., Markov decision processes and dynamic programming techniques) before we go to model-free prediction and control algorithms such as TD-learning, SARSA and Q-learning. We will also get the general idea behind value function approximation techniques such as Deep Q-Networks (DQN) and study advanced policy-gradient and actor-critic methods.
Students will then explore different intermediate to advanced areas of RL, for which they will prepare a presentation as well as code examples. The presentations will take place at the end of the semester (or beginning of the summer break) as a block seminar (we doodle dates that fit for the students and assign slots on a best-effort basis).
Table of Contents
Lecture
Topic
0.01 Opening Remarks
Lecture 1: Introduction (Q&A Session: 21.04.2020 13:00)
1.01 Introduction to Reinforcement Learning
1.02 Markov Decision Processes
Lecture 2: Dynamic Programming (Q&A Session: 28.04.2020 13:00)
2.01 Introduction to Dynamic Programming
2.02 Value Iteration
2.03 Policy Iteration
2.04 Example: Frozen lake with Value Iteration
2.05 Summary
Lecture 3: Model-free Prediction (Q&A Session: 05.05.2020 13:00, pdf)
3.01 Introduction to Model-free Reinforcement Learning
3.02 Monte-Carlo Learning
3.03 Time-Difference Learning
3.04 Example: Frozen Lake with TD-Learning
Lecture 4: Model-free Control (Q&A Session: 12.05.2020 13:00)
4.01 Model-Free Control
4.02 Example: Intro to OpenAI Gym
4.03 Example: Frozen Lake with Q-Learning
4.04 Summary
Lecture 5: Value Function Approximation (Q&A Session: 19.05.2020 13:00)
5.01 Value Function Approximation
5.02 Linear Value Function Approximation
5.03 Deep Q-Networks
5.04 Example: Cartpole with DQNs
5.05 Summary
Lecture 6: Policy-based RL (Q&A Session: 26.05.2020 13:00)
6.01 Introduction to Policy-based Reinforcement Learning
6.02 Policy Gradients
6.03 Example: Monte-Carlo Policy Gradient
6.04 Actor-Critics
Additional Q&A Session: 23.06.2020 12:00 (pdf)
Notes/Remarks:
- in Lecture 5.03 there is a small mistake: in DQN we sample the action to be taken by the agent from the evaluation network and *not* from the target network. The target is solely used to generate the Q-targets!
Student Presentations
The student presentations should take approx. 30 minutes (including Q&A) and be held in English. We expect the student to present runnable code as a part of their presentations. The students should hence be familiar with python. Further we assume that the students to have a deeper understanding of linear algebra and analysis, multivariate statistics, and machine learning in general.
All presentations are held in our zoom meeting slot from 12:00 – 14:00 (s.t. – we will start without delay!) on the respective dates.
Date | Student | Topic | Material |
|---|---|---|---|
30.06. | Sven Lorenz | Multi-Agent Reinforcement Learning (literature) | |
Sebastian Fischer | MAML: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (literature) | ||
07.07. | Asmik Nalmpatian | Trust-Region Policy Optimization (TRPO) (literature) | |
Tobias Weber | Batch RL (literature) | ||
Jonas Schweisthal | World Models (literature) | ||
14.07. | Amadeu Scheppach | Proximal Policy Optimization (PPO) (literature) + Example: DD-PPO: Near-Perfect PointGoal Navigators (literature) | |
Matthias Gruber | Model-based Reinforcement Learning (literature) | ||
Hyeyoung Park | Explainable Reinforcement Learning (literature) | ||
21.07. | Tobias Altmiks | Deep Deterministic Policy Gradient (DDPG) & Twin-Delayed DDPG (TD3) (literature) | |
28.07. | Alexander Pohl | Asynchronous Advantage Actor-Critic (A3C) (+A2C) (literature) + Unsupervised Auxilary Tasks | |
Lennart Schneider | Option-Critics (literature)+Hierarchical Reinforcement Learning (literature) | ||
Stefan Depperschmidt | Curiosity (literature) | ||
29.07. | Rifat Amin | Imitation Learning (literature) + GAIL: Generative Adversarial Imitation Learning (literature) |
Short Presentations
The short presentations should take approx. 10 minutes and focus on a paper from the recent ICLR conference.
| Student | Topic | Slides |
|---|---|---|
| Adelina Khoroshevskaya | Qureshi et al.: Composing Task-Agnostic Policies with Deep Reinforcement Learning [paper] | |
| Ilona Bamiller | Hafner et al: Dream to Control: Learning Behaviors by Latent Imagination [paper] | |
| Julian Raith | Freeman et al.: Learning to Predict without looking ahead: World Models without Forward Prediction [paper] | pdf |
| Sergio Antelo | Casanova et al.: Reinforced Active Learning for Image Segmentation [paper] | |
| Pranav Ragupathy | Freeman et al.: Learning to Predict without looking ahead: World Models without Forward Prediction [paper] | |
| Viet Tran | Casanova et al.: Reinforced Active Learning for Image Segmentation [paper] | pdf |
| Xiao-Yin Janet To | Rajeswaran et al.: EPOpt: Learning Robust Neural Network Policies Using Model Ensembles [paper] |
Exams
You can find the scheduling of the exams here.
Evaluation
You can find the results of the lecture and seminar evaluation here: SoSe_2020-Reinforcement_Learning_–_Seminar
Literature
While there is particular literature given in the slides of the videos the following list serves as a general basis to get into the topic but also to go deeper at particular points.
- Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. A Bradford Book, Cambridge, MA, USA. [link]
- Bellman, R.E. 1957. Dynamic Programming. Princeton University Press, Princeton, NJ. Republished 2003: Dover, ISBN 0-486-42809-5.
- UC Berkeley CS188: Intro to AI [link]
- University College London Course on RL [link]
- Advanced Deep Learning and Reinforcement Learning (UCL + DeepMind) [link]
- https://cs.stanford.edu/people/karpathy/reinforcejs/gridworld_dp.html
- https://cs.stanford.edu/people/karpathy/reinforcejs/gridworld_td.html
Interesting talks, articles, and blog-posts:
- Joelle Pineau: Reproducible, Reusable, and Robust Reinforcement Learning [youtube]
- David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | AI Podcast #86 with Lex Fridman [youtube]
- Technion Research: Why does reinforcement learning not work (for you)? [link]
- RL algorithms quick overview [link]
Code examples and Exercises:
- GitHub Repo of Denny Britz: https://github.com/dennybritz/reinforcement-learning/tree/master/DP