10-403 Deep RL | Schedule

Date	Lecture	Readings	Logistics
W 01/17	Lecture #1 : Introduction to Reinforcement and Representation Learning [ slides ]	S & B Textbook, Ch1 Smith & Gasser. The Development of Embodied Cognition - Six Lessons from Babies Dan Wolpert't talk The real reason for brains
F 01/19	Recitation #1: Neural Nets, TensorFlow & Keras, OpenAI Gym, Bandits [ slides ]	G, B & C Textbook, Ch9, Ch10 Tensorflow tutorial notebook OpenAI Gym tutorial notebook PyTorch tutorial notebook The TensorFlow High Level (Keras) API
M 01/22	Lecture #2 : Multi-armed Bandits [ slides ]	S & B Textbook, Ch2 2.1-2.7 Russo et al. A Tutorial on Thompson Sampling, Ch1-Ch4. Optional after Ch4
W 01/24	Lecture #3 : Markov Decision Processes, Value Iteration, Policy Iteration [ slides ]	S & B Textbook, Ch3, Ch4 The Path perspective on Value Learning (blogpost)	HW1 out (tentative)
F 01/26	Recitation #2: Bandits, MDPs & HW1 [ slides ]
M 01/29	Lecture #4 : Monte Carlo Learning and Temporal Difference Learning [ slides ]	S & B Textbook, Ch5, Ch6
W 01/31	Lecture #5 : Monte Carlo Learning and Temporal Difference Learning (Cont.) [ slides ]	S & B Textbook, Ch5, Ch6
F 02/02	Recitation #3: No Recitation [ slides ]
M 02/05	Lecture #6 : Planning, Monte Carlo Tree search [ slides ]	S & B Textbook, Ch8.11
W 02/07	Lecture #7 : Function approximation in prediction and control, Deep Q-learning [ slides ]	S & B Textbook, Ch6, Ch7 7.1-7.3 S & B Textbook, Ch9.1-9.3, 9.6 and Ch10.1 Mnih et al. Playing Atari with Deep Reinforcement Learning Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning
F 02/09	Recitation #4: MCTS, TD Learning, Deep Q Learning, HW2 (DQN) [ slides ]
M 02/12	Lecture #8 : Policy gradients, REINFORCE, Actor-Critic methods [ slides ]	Mnih et al. Asynchronous Methods for Deep Reinforcement Learning S & B Textbook, Ch13 http://karpathy.github.io/2016/05/31/rl/	HW1 due 11:59pm, HW2 out (tentative)
W 02/14	Lecture #9 : Natural PG, PPO, TRPO [ slides ]	(optional) Schulman et al. Trust Region Policy Optimization Schulman et al. Proximal Policy Optimization Algorithms (optional) Rajeswaran et al. Towards Generalization and Simplicity in Continuous Control
F 02/16	Recitation #5: HW2 (PG) and Quiz 1 Review [ slides ]
M 02/19	Lecture #10 : Natural PG, PPO, TRPO (cont.) [ slides ]	(optional) Schulman et al. Trust Region Policy Optimization Schulman et al. Proximal Policy Optimization Algorithms (optional) Rajeswaran et al. Towards Generalization and Simplicity in Continuous Control
W 02/21	Lecture #11 : Deterministic Policy gradient, re-parametrized PG [ slides ]	Lillicrap et al. Continuous control with deep reinforcement learning
F 02/23	Quiz 1
M 02/26	Lecture #12 : Evolutionary methods for policy search [ slides ]	Salimans et al. Evolution Strategies as a Scalable Alternative to Reinforcement Learning (optional) Nikolaus Hansen. The CMA Evolution Strategy - A Tutorial, optional Antoine Cully et al. Robots that can adapt like animals
W 02/28	Lecture #13 : Imitation learning, behavior cloning [ slides ]	(optional) Chen et al. Learning by Cheating Bagnell. An Invitation to Imitation, Up To Page 10 Bojarski et al. End to End Learning for Self-Driving Cars
F 03/01	Recitation #6: Solutions to Quiz 1 [ slides ]
M 03/04	Spring Break - No Classes
W 03/06	Spring Break - No Classes
F 03/08	Spring Break - No Classes
M 03/11	Lecture #14 : Multi-goal RL and IL [ slides ]	Ding et al. Goal-conditioned Imitation Learning Zeng et al. Transporter Networks Rearranging the Visual World for Robotic Manipulation Andrychowicz et al. Hindsight Experience Replay	HW3 out (tentative), HW2 due 11:59PM
W 03/13	Lecture #15 : AlphaGo, AlphaGoZero, AlphaZero [ slides ]	(optional) David Silver et al. Mastering the game of Go with deep neural networks and tree search David Silver et al. Mastering the game of Go without human knowledge David Silver et al. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
F 03/15	Recitation #7: HW3 [ slides ]
M 03/18	Lecture #16 : MBRL in explicit and observable low-dimensional state spaces [ slides ]	Gonzalez et al. Learning to Simulate Complex Physics with Graph Networks Chua et al. Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
W 03/20	Lecture #17 : MBRL from Sensory Input, Planning in Sensory Space [ slides ]	Oh et al. Action-Conditional Video Prediction using Deep Networks in Atari Games
F 03/22	Recitation #8: Quiz 2 Review & HW4 [ slides ]		HW4 out (tentative), HW3 due 11:59PM
M 03/25	Lecture #18 : MBRL (cont.) Planning in a Latent State Space [ slides ]	Hansen et al. Temporal Difference Learning for Model Predictive Control DeepMind Blog Post MuZero:Mastering Go, chess, shogi and Atari without rules Julian Schrittwieser et al. Mastering Atari, Go, chess and shogi by planning with a learned model
W 03/27	Lecture #19 : MBRL (cont.) Stochastic Latent Dynamics Models [ slides ]	Hafner, et.al Dream to Control:Learning Behaviors by Latent Imagination Carl Doersch et al. Tutorial on Variational Autoencoders
F 03/29	Quiz 2
M 04/01	Lecture #20 : Intelligent Exploration [ slides ]	(optional) Pathak et al. Curiosity-driven Exploration by Self-supervised Prediction Burda et al. Large-Scale Study of Curiosity-Driven Learning Savinov et al. Episodic Curiosity through Reachability Ecoffet et al. Go-Explore: a New Approach for Hard-Exploration Problems Salimans et al. Learning Montezuma's Revenge from a Single Demonstration
W 04/03	Recitation #9: HW4 Slides/OH [ slides ]
F 04/05	Recitation #10: Intelligent Exploration [ slides ]		HW5 out (tentative), HW4 due 11:59PM
M 04/08	Lecture #21 : Sim2Real Transfer [ slides ]	Kumar et al. Rapid Motor Adaptation for Legged Robots Tobin et al. Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World (Optional) Muller et al. Driving Policy Transfer via Modularity and Abstraction Akkaya et al. Solving Rubik’s Cube with A Robot Hand
W 04/10	Lecture #22 : Homework 5 and Solutions to Quiz 2 [ slides ]
F 04/12	Spring Carnival - No Classes
M 04/15	Lecture #23 : Diffusion Models for Imitation and Model-based RL [ slides ]	Luo Understanding Diffusion Models:A Unified Perspective Janner et al. Planning with Diffusion for Flexible Behavior Synthesis Pearce et al. Imitating Human Behaviour with Diffusion Models
W 04/17	Lecture #24 : Diffusion Models for Imitation and Model-based RL (cont.) [ slides ]	Luo Understanding Diffusion Models:A Unified Perspective Janner et al. Planning with Diffusion for Flexible Behavior Synthesis Pearce et al. Imitating Human Behaviour with Diffusion Models
F 04/19	Lecture #25 : Language and Robot Control [ slides ]	Radford et al. Learning Transferable Visual Models From Natural Language Supervision Shridhar et al. CLIPort What and Where Pathways for Robotic Manipulation Brown et al.Language Models are Few-Shot Learners Liang et al.Code as Policies:Language Model Programs for Embodied Control
M 04/22	Lecture #26 : Offline Reinforcement Learning [ slides ]	Fujimoto et al. Off-Policy Deep Reinforcement Learning without Exploration Mandlekar et al. IRIS:Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data	HW5 due 11:59PM
W 04/24	Lecture #27 : Visual Imitation Learning [ slides ]	Peng et al. SFV Reinforcement Learning of Physical Skills from Videos Baker et al. Video PreTraining (VPT):Learning to Act by Watching Unlabeled Online Videos
F 04/26	Recitation #11: Quiz 3 Review [ slides \| slides 2 ]
04/30	Quiz 3, 8:30 AM - 11:30 AM, GHC 4307

W 01/17

Lecture #1 :
Introduction to Reinforcement and Representation Learning
[ slides ]