Deep Reinforcement Learning and Control
Fall 2018, CMU 10703

• Katerina: Tuesday 1.30-2.30pm, 8107 GHC
  
• Tom: Monday 1:20-1:50pm, Wednesday 1:20-1:50pm, Immediately after class, just outside the lecture room
  

• Nicholay Topin : Monday 3pm-4pm, GHC 8123
  
• Balarama Buddharaju : Tuesday 9:30am-10:30am, 5th floor commons
  
• Anshu Aviral : Tuesday 11am-12pm, 6th floor commons
  
• Siddharth Ancha : Wednesdays 11am-12pm, GHC 8021
  
• Aditya Siddhant : Thursday 5pm-6pm, LTI 5th floor commons
  
• Shihui Li : Thursday 10am-11am, GHC 5th floor commons
  
• Eric Nie : Thursday 1pm-2pm, GHC 5th floor commons
  
• Brynn Edmunds
  

• Class goals
• Schedule
• Resources
• Assignments and grading
• Prerequisites

Class goals

• Implement and experiment with existing algorithms for learning control policies guided by reinforcement, demonstrations and intrinsic curiosity.
• Evaluate the sample complexity, generalization and generality of these algorithms.
• Be able to understand research papers in the field of robotic learning.
• Try out some ideas/extensions on your own. Particular focus on incorporating sensory input from visual sensors.

Prerequisites

Schedule

Resources

Readings

1. [SB] Sutton & Barto, Reinforcement Learning: An Introduction
2. [GBC] Goodfellow, Bengio & Courville, Deep Learning

1. Smith & Gasser, The Development of Embodied Cognition: Six Lessons from Babies
2. Silver, Huang et al., Mastering the Game of Go with Deep Neural Networks and Tree Search
3. Houthooft et al., VIME: Variational Information Maximizing Exploration
4. Stadie et al., Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
5. Bagnell, An Invitation to Imitation
6. Nguyen, Imitation Learning with Recurrent Neural Networks
7. Bengio et al., Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
8. III et al., Searn in Practice
9. Bojarski et al., End to End Learning for Self-Driving Cars
10. Guo et al., Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning
11. Rouhollah et al., Learning real manipulation tasks from virtual demonstrations using LSTM
12. Ross et al., Learning Monocular Reactive UAV Control in Cluttered Natural Environments
13. Ross et al., A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
14. Ziebart et al., Navigate Like a Cabbie: Probabilistic Reasoning from Observed Context-Aware Behavior
15. Abbeel et al., Apprenticeship Learning via Inverse Reinforcement Learning
16. Ho et al., Model-Free Imitation Learning with Policy Optimization
17. Finn et al., Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
18. Ziebart et al., Maximum Entropy Inverse Reinforcement Learning
19. Ziebart et al., Human Behavior Modeling with Maximum Entropy Inverse Optimal Control
20. Finn et al., Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
21. Tassa et al., Synthesis and Stabilization of Complex Behaviors through Online Trajectory Optimization
22. Watter et al., Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
23. Levine et al., Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
24. Levine et al., Guided Policy Search
25. Levine et al., End-to-End Training of Deep Visuomotor Policies
26. Kumar et al., Learning Dexterous Manipulation Policies from Experience and Imitation
27. Mishra et al., Prediction and Control with Temporal Segment Models
28. Lillicrap et al., Continuous control with deep reinforcement learning
29. Heess et al., Learning Continuous Control Policies by Stochastic Value Gradients
30. Mordatch et al., Combining model-based policy search with online model learning for control of physical humanoids
31. Rajeswaran et al., EPOpt: Learning Robust Neural Network Policies Using Model Ensembles
32. Zoph et al., Neural Architecture Search with Reinforcement Learning
33. Tzeng et al., Adapting Deep Visuomotor Representations with Weak Pairwise Constraints
34. Ganin et al., Domain-Adversarial Training of Neural Networks
35. Rusu et al., Sim-to-Real Robot Learning from Pixels with Progressive Nets
36. Hanna et al., Grounded Action Transformation for Robot Learning in Simulation
37. Christiano et al., Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
38. Xiong et al., Supervised Descent Method and its Applications to Face Alignment
39. Duan et al., One-Shot Imitation Learning
40. Lake et al., Building Machines That Learn and Think Like People
41. Andrychowicz et al., Learning to learn by gradient descent by gradient descent
42. Finn et al., Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
43. Silver et al., Mastering the Game of Go without Human Knowledge
44. Mnih et al., Playing Atari with Deep Reinforcement Learning

General references

• Szepesvari, Algorithms for Reinforcement Learning
• Bertsekas, Dynamic Programming and Optimal Control, Vols I and II
• Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming
• Powell, Approximate Dynamic Programming

Online courses

• Rich Sutton's class: Reinforcement Learning for Artificial Intelligence, Fall 2016
• John Schulman's and Pieter Abeel's class: Deep Reinforcement Learning, Fall 2015
• Sergey Levine's, Chelsea Finn's and John Schulman's class: Deep Reinforcement Learning, Spring 2017
• Abdeslam Boularias's class: Robot Learning Seminar
• Pieter Abeel's class: Advanced Robotics, Fall 2015
• Emo Todorov's class: Intelligent control through learning and optimization, Spring 2015
• David Silver's class: Reinforcement learning

AWS Resources

• If you are not officially registered for this class, you are not allowed to request resources. We will be checking before we submit requests, so please do not request access to them.
• We will be offering AWS resources. All students should join AWS educate using this link: https://aws.amazon.com/education/awseducate/ using their @andrew.cmu.edu email address. If you do not use your andrew email address, your resources may be denied. You should do this as soon as possible, as it can take time to set up your accounts.
• AWS NOTE: You need to back this account with your own credit/debit card and we will give out allocation codes of $50, this is important as should you go over this $50 it will start charging to your card, please be sure to keep an eye on your funds and not forget to terminate instances. The university holds no responsibility in paying for additional usage.
• We will ask you to complete an Allocation Form in order to apply for your resources. This will be made available later in the semester. Note: HW1 does not require AWS resources.

Assignments and grading

Homeworks

Projects

Grace Day/Late Homework Policy

• Homeworks: Each student has a total of 4 grace days that may be applied to the homework assignments. No more than 3 grace days may be used on any single assignment. Any assignment submitted more than 3 days past the deadline will get zero credit. Grace days will be subtracted from both students in the homework team. E.g. an assignment submitted 1 day late will result in both team members losing 1 grace day from their total allotment.
• Projects: Each team will be allotted a total of 3 grace days on the project, separate from homework grace days (unused grace days from the homework assignments CANNOT be applied to the project). Project late days can be on the midway and final report, but not on the poster presentation. Any project submitted more than 3 days past the deadline will get zero credit.

Course Policies

Auditing

• Official auditing of the course (i.e. taking the course for an “Audit” grade) is not permitted this semester.
• Unofficial auditing of the course (i.e. watching the lectures online or attending them in person, but not turning in homeworks to grade) is welcome and permitted without prior approval. We give priority to students who are officially registered for the course, so informal auditors may only take a seat in the classroom is there is one available 10 minutes after the start of class. Unofficial auditors will not be given access to course materials such as homework assignments and exams.
• Please email Brynn if you need further clarification.

Extensions

• Medical Emergencies: If you are sick and unable to complete an assignment or attend class, please go to University Health Services. For minor illnesses, we expect grace days or our late penalties to provide sufficient accommodation. For medical emergencies (e.g. prolonged hospitalization), students may request an extension afterwards and should include a note from University Health Services.
• Family/Personal Emergencies: If you have a family emergency (e.g. death in the family) or a personal emergency (e.g. mental health crisis), please contact your academic adviser or Counseling and Psychological Services (CaPS). In addition to offering support, they will reach out to the instructors for all your courses on your behalf to request an extension.
• University-Approved Absences: If you are attending an out-of-town university approved event (e.g. multi-day athletic/academic trip organized by the university), you may request an extension for the duration of the trip. You must provide confirmation of your attendance, usually from a faculty or staff organizer of the event.

Pass/Fail Policy

Online and Waitlisted Students

• All lecture videos will be recorded and made available online. We are currently working with the administration to try and create an online section for this course (10-703 B) so that we can work on getting everybody off of the waitlist and officially enrolled. Please be patient, as this may take time to complete. Past experience suggests that there will be sufficient seats in the classroom for everybody who wants to take the course, so we are optimistic that all students on the waitlist are likely to be able to register within the first few weeks.
• Waitlisted students should complete all homework assignments with the rest of the class.
• The first couple lectures are likely to be quite full -- so it'd be best for waitlist students to use the livestream. We'll let you know when seats start to become available. Once that happens, you are welcome to take a physical seat (GHC 4401) if there is an open one 5 minutes after class has started (e.g. 12:05pm)

Students with course conflicts

Academic Integrity (Read this carefully!)

Collaboration among Students

• The purpose of student collaboration is to facilitate learning, not to circumvent it. Studying the material in groups is strongly encouraged. It is also allowed to seek help from other students in understanding the material needed to solve a particular homework problem, provided no written notes (including code) are shared, or are taken at that time, and provided learning is facilitated, not circumvented. The actual solution must be done by each student alone.
• The presence or absence of any form of help or collaboration, whether given or received, must be explicitly stated and disclosed in full by all involved. Specifically, each assignment solution must include answering the following questions:
  1. Did you receive any help whatsoever from anyone in solving this assignment? Yes / No.
     • If you answered 'yes', give full details: ____________
     • (e.g. "Jane Doe explained to me what is asked in Question 3.4")
  2. Did you give any help whatsoever to anyone in solving this assignment? Yes / No.
     • If you answered 'yes', give full details: _____________
     • (e.g. "I pointed Joe Smith to section 2.3 since he didn't know how to proceed with Question 2")
  3. Did you find or come across code that implements any part of this assignment ? Yes / No. (See below policy on "found code")
     • If you answered 'yes', give full details: _____________
     • (book & page, URL & location within the page, etc.).
• If you gave help after turning in your own assignment and/or after answering the questions above, you must update your answers before the assignment's deadline, if necessary by emailing the course staff.
• Collaboration without full disclosure will be handled severely, in compliance with CMU's Policy on Cheating and Plagiarism.

Previously Used Assignments

Policy Regarding "Found Code"

Duty to Protect One's Work

Penalties for Violations of Course Policies

1. The penalty for the first violation is a one-and-a-half letter grade reduction. For example, if your final letter grade for the course was to be an A-, it would become a C+
2. The penalty for the second violation is failure in the course, and can even lead to dismissal from the university.

Accommodations for Students with Disabilities