1. Jan 24  Course Introduction  Course Overview  (Sungjin Ahn)
 Overview on Probabilistic Agent Leanring  (Sungjin Ahn)
 Variational Autoencoders  (Gautam Singh)
 *AutoEncoding Variational Bayes
 Importance Weighted Autoencoders

2. Jan 31  DRL I & Advances in Variational Inference I  Deep Reinforcement Learning: Part I  (Sungjin Ahn)
 Advanced VAE  1 (Mun Kim)
 DRAW: A Recurrent Neural Network For Image Generation
 Variational Inference with Normalizing Flows
 (optional) Towards Conceptual Compression

3. Feb 7  DRL II & Advances in Variational Inference II  Deep Reinforcement Learning: Part II  (Sungjin Ahn)
 Advanced VAE  2 (Bingchen Liu)
 Categorical Reparameterization with GumbelSoftmax
 REINFORCE: )>=A@(! 7?&%31>= <:;9&%8760&%54 &%3120/.&%),+)*('%&%#$"!)>=A@(! 7?&%31>= <:;9&%8760&%54 &%3120/.&%),+)*('%&%#$"!Simple Statistical GradientFollowing Algorithms for Connectionist ...Simple Statistical GradientFollowing Algorithms for Connectionist ...Simple Statistical GradientFollowing Algorithms for Connectionist ...Simple Statistical GradientFollowing Algorithms for Connectionist ...◊Simple Statistical GradientFollowing Algorithms for Connectionist ...

4. Feb 14  Bayesian Neural Networks & Generative Temporal Models  Bayesian Neural Networks (Weihao Sun)
 Weight Uncertainty in Neural Networks
 Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
 Generative Temporal Models  1 (Gautam Sing)
 A Recurrent Latent Variable Model for Sequential Data
 Structured Inference Networks for Nonlinear State Space Models
 (optional)
 Sequential Neural Models with Stochastic Layers
 Deep Variational Bayes Filters: Unsupervised Learning of State Space ...

5. Feb 21  Generative Temporal Models (cont.) & Memory  Generative Temporal Models  2 (Jindong Jiang)
 AutoEncoding Sequential Monte Carlo
 Deep Variational Reinforcement Learning for POMDPs
 (optional)
 Variational Sequential Monte Carlo
 Memory 1: Temporal Models with External Memory (Han Wu)

6. Feb 28  Memory (cont.) & Representation  Memory 2: Generative Distributed Memory (Vladimir Ivanov)
 The Kanerva Machine: A Generative Distributed Memory
 Learning Attractor Dynamics for Generative Memory
 (optional) Approximating Bayesian inference with a sparse distributed memory system
 Representation 1: BetaVAE (Ligong Han)
 betaVAE: Learning Basic Visual Concepts with a Constrained Variational Framework
 Understanding disentangling in betaVAE
 (optional) Isolating Sources of Disentanglement in VAEs

7. Mar 7  Representation & Structured Perception  Representation 2: Contrastive Predictive Coding (Eunyoung Kim)
 Representation Learning with Contrastive Predictive Coding
 Neural Predictive Belief Representations
 Structured Perception  1
 AIR: Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
 SQAIR: Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

8. Mar 14 
9. Mar 21  SPRING RECESSION

10. Mar 28  Structured Perception & GraphRelation  Structured Perception  2
 RNEM: Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
 Unsupervised Learning of 3D Structure from Images
 MONet: Unsupervised Scene Decomposition and Representation
 Graph & Relation
 Neural Relational Inference for Interacting Systems
 Graph networks as learnable physics engines for inference and control
 Relational recurrent neural networks

11. Apr 4  Meta & Continual Learning  Meta Learing
 Towards a Neural Statistician
 Amortized Bayesian MetaLearning
 (optional) Recasting GradientBased MetaLearning as Hierarchical Bayes
 (optional) The Variational Homoencoder: Learning to learn high capacity generative models from few examples
 (optional) VERSA: Versatile and Efficient Fewshot Learning

12. Apr 11  Generative Query Networks (GQN) and Program Learning  GQN & Neural Processes
 Neural Scene Representation and Rendering
 Neural Processes
 (optional) CGQN: Consistent Generative Query Networks
 (optional) Attentive Neural Processes

13. Apr 18  ModelBased RL  ModelBased RL  1: ImaginationAugmented Agents
 I2A: ImaginationAugmented Agents for Deep Reinforcement Learning
 I2ASS: Learning and Querying Fast Generative Models for Reinforcement ...
 ModelBased RL  2: World Models

14. Apr 25  Unsupervised RL (Exploration, Intrinsic Motivation, Options)  Options
 Variational Intrinsic Control
 Diversity is All You Need: Learning Skills without a Reward Function
 (optional) Variational Option Discovery Algorithms

15. May 2 TBD (Probabilistic Reinforcement Learning)  Probabilistic Reinforcement Learning  1
 Soft QLearning: Reinforcement Learning with Deep EnergyBased Policies
 Soft ActorCritic: OffPolicy Maximum Entropy Deep Reinforcement ...
 Probabilistic Reinforcement Learning  2
 Latent Space Policies for Hierarchical Reinforcement Learning
TBD (Spatial Navigation)
 Spatial Learning  1
 VectorBased Navigation Using GridLike Representations in Artificial Agents (Nature 18)
 Neural Map: Structured Memory for Deep Reinforcement Learning (ICLR 18)
 Spatial Learning  2
 Emergence of GridLike Representations by Training Recurrent Neural Networks to Perform Spatial Localization (ICLR 18)
 Semiparametric Topological Memory for Navigation (ICLR 18)
 Spatial Learning  3
 Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction (ICLR 19)

16. May 9  Final Project Presentation
