Patrick Emami
Updates on my machine learning research, summaries of papers, and blog posts
Blog / About Me / Paper Summaries

Deep Reinforcement Learning


Addressing Function Approximation Error in Actor-Critic Methods & Discriminator-Actor-Critic- Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
// Fujimoto et al., 2018, Kostrikov, et al. 2018


Recurrent Environment Simulators
// Chiappa, et al., 2017


Learning To Navigate in Complex Environments
// Mirowski, et al., 2016


Unifying Count-Based Exploration and Intrinsic Motivation
// Bellemare, et al., 2016


Hierarchical Deep Reinforcement Learning- Integrating Temporal Abstraction and Intrinsic Motivation
// Kulkarni, et al., 2016


Variational Information Maximizing Exploration
// Houthooft, et al., 2016 ~ OpenAI


Deep Exploration via Bootstrapped DQN
// Osband, et al., 2016


Asynchronous Methods for Deep Reinforcement Learning
// Mnih, et al., 2016


Neural Fitted Q Iteration
// Riedmiller, M. 2005


Mastering the Game of Go with Deep Neural Networks and Tree Search
// Silver, et al., 2016


Dueling Network Architectures for Deep Reinforcement Learning
// Wang, de Freitas, Lanctot, 2016


Prioritized Experience Replay
// Schaul, Quan, Antonoglou, Silver, 2016


Incentivizing Exploration in Reinforcement Learning with Deep Predictive Models
// Bradly C. Stadie, Sergey Levine, Pieter Abbeel, 2015

Computer Vision


Learning From Demonstrations in the Wild
// Behbahani et al., 2018


Tracking Occluded Objects and Recovering Incomplete Trajectories by Reasoning about Containment Relations and Human Actions
// Liang, Zhu, Zhu, 2018


DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
// Lee, et al., 2016


Fast, Exact, and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
// Chandra, Kokkinos, 2016


Pixel Recursive Super Resolution
// Dahl, Norouzi, Shlens, 2017


Deep Residual Learning for Image Recognition
// He, et al., 2015

Reinforcement Learning Theory


RUDDER: Return Decomposition for Delayed Rewards
// Arjona-Medina, Gillhofer, et al., 2018


Horde: A Scalable Real-time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction
// Sutton, et al. 2011


Towards Deep Symbolic Reinforcement Learning
// Garnelo, et al., 2017


Linear Least-Squares Algorithms for Temporal Difference Learning
// Bradtke, Barto, 1996


Memory Transformations Enhances Reinforcement Learning in Dynamic Environments
// Santoro, Frankland, Richards, 2016


The Optimal Control of Partially Observable Markov Processes Over a Finite Horizon
// Sondik, et al., 1973


Intrinsically Motivated Reinforcement Learning
// Singh, et al., 2004


Cooperative Inverse Reinforcement Learning
// Hadfield-Menell, et al., 2016

Generative Adversarial Networks


Progressive Growing of GANs for Improved Quality, Stability, and Variation
// Karras, et al., 2018


A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
// Finn, Christiano, Abbeel, Levine, 2016


InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
// Chen, et al., 2016

Natural Language Processing


Z-Forcing: Training Stochastic Recurrent Networks
// Goyal, et al., 2017


Distributed Representations of Words and Phrases and their Compositionality
// Mikolov, et al., 2013


A Neural Probabilistic Language Model
// Bengio, et al., 2003

Deep Learning Theory


What Can Neural Networks Reason About?
// Xu, Li, Zhang, Du, Kawarabayashi, Jegelka, 2020


Convexified Convolutional Neural Networks
// Zhang, Liang, Wainwright, 2016


Geometric deep learning: going beyond Euclidean data
// Bronstein, 2017


Deep Learning via Hessian-Free Optimization
// James Martens, 2010


Batch Renormalization-Towards Reducing Minibatch Dependence in Batch-Normalized Models
// Ioffe, 2017

Artificial General Intelligence


Interaction Networks for Learning about Objects, Relations, and Physics
// Battaglia, et al., 2016


Building Machines That Learn and Think Like People
// Lake, et al., 2016


Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution
// Baker, et al., 2011

General Machine Learning


Nonlinear Dimensionality Reduction by Locally Linear Embedding
// Roweis, Saul, 2000


A Global Geometric Framework for Nonlinear Dimensionality Reduction
// Tenenbaum, et al. 2000


The Markov Chain Monte Carlo Revolution
// Persi Diaconis, 2009


Topology and Data
// Gunnar Carlsson, 2009


Machine Learning in Genomic Medicine: A Review of Computational Problems and Data Sets
// Leung, Michael K. K., 2016


Multipolicy Decision-Making for Autonomous Driving via Changepoint-based Behavior Prediction
// Galceran, Cunningham, Eustice, Olson, 2015


Intention-Aware Risk Estimation: Field Results
// Lefevre, Vasquez, Laugier, Ibanez-Guzman, 2015


How To Write A Great Research Paper (Professor Simon Peyton Jones)
// Professor Simon Peyton Jones