This will contain my notes for research papers that I've read. The papers are arranged according to four broad categories and then further numbered on a (1) to (5) scale where a (1) means I have only barely skimmed it, while a (5) means I feel confident that I understand almost everything about the paper. Within a single year, these papers should be organized according to publication date, which gives an idea of how these contributions were organized.
The links here go to my paper summaries (if I have them), otherwise I probably have put that task somewhere in my long TODO list for papers to read/write about. I won't be listing all relevant papers, just the ones that I'm mostly likely to try and summarize here.
(Not counting Deep Reinforcement Learning; see the "Reinforcement Learning" category)
- Understanding Deep Learning Requires Rethinking Generalization, ICLR 2017 (1)
- NIPS 2016 Tutorial: Generative Adversarial Networks, arXiv (1)
- Visualizing and Understanding Recurrent Networks, ICLR Workshop 2016 (1)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, ICML 2015 (4)
- DRAW: A Recurrent Neural Network For Image Generation, ICML 2015 (2)
- The Loss Surfaces of Multilayer Networks, AISTATS 2015 (3)
- Generative Adversarial Nets, NIPS 2014 (4)
- Recurrent Models of Visual Attention, NIPS 2014 (4)
(Mostly of the deep variety)
- Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning, preprint (5)
- Stochastic Neural Networks for Hierarchical Reinforcement Learning, arXiv (4)
- #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning, arXiv (4)
- RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning, arXiv (3)
- Modular Multitask Reinforcement Learning with Policy Sketches, arXiv (1)
- Deep Visual Foresight for Planning Robot Motion, ICRA 2017 (3)
- Multilateral Surgical Pattern Cutting in 2D Orthotropic Gauze with Deep Reinforcement Learning Policies for Tensioning, ICRA 2017 (5)
- Value Iteration Networks, NIPS 2016 (4)
- Generative Adversarial Imitation Learning, NIPS 2016 (3)
- Deep Exploration via Bootstrapped DQN, NIPS 2016 (1)
- VIME: Variational Information Maximizing Exploration, NIPS 2016 (1)
- Cooperative Inverse Reinforcement Learning, NIPS 2016 (1)
- Unifying Count-Based Exploration and Intrinsic Motivation, NIPS 2016 (1)
- Principled Option Learning in Markov Decision Processes, EWRL 2016 (4)
- Taming the Noise in Reinforcement Learning via Soft Updates, UAI 2016 (4)
- Asynchronous Methods for Deep Reinforcement Learning, ICML 2016 (3)
- Benchmarking Deep Reinforcement Learning for Continuous Control, ICML 2016 (4)
- Model-Free Imitation Learning with Policy Optimization, ICML 2016 (2)
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization, ICML 2016 (1)
- Dueling Network Architectures for Deep Reinforcement Learning, ICML 2016 (1)
- Prioritized Experience Replay, ICLR 2016 (4)
- High-Dimensional Continuous Control Using Generalized Advantage Estimation, ICLR 2016 (1)
- Continuous Control with Deep Reinforcement Learning, ICLR 2016 (1)
- End-to-End Training of Deep Visuomotor Policies, JMLR 2016 (1)
- Deep Reinforcement Learning with Double Q-learning, AAAI 2016 (2)
- Mastering the Game of Go with Deep Neural Networks and Tree Search, Nature 2016 (1)
- Learning Continuous Control Policies by Stochastic Value Gradients, NIPS 2015 (1)
- Deep Recurrent Q-Learning for Partially Observable MDPs, AAAI-SDMIA 2015 (5)
- Trust Region Policy Optimization, ICML 2015 (2)
- Probabilistic Inference for Determining Options in Reinforcement Learning, ICML Workshop 2015 (3)
- Massively Parallel Methods for Deep Reinforcement Learning, ICML Workshop 2015 (1)
- Human-Level Control Through Deep Reinforcement Learning, Nature 2015 (5)
- Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning, NIPS 2014 (3)
- Playing Atari with Deep Reinforcement Learning, NIPS Workshop 2013 (5)
- A Tutorial on Linear Function Approximators for Dynamic Programming and Reinforcement Learning, Foundations and Trends in Machine Learning 2013 (4)
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning, AISTATS 2011 (3)
- Maximum Entropy Inverse Reinforcement Learning, AAAI 2008 (4)
- A Conceptual Introduction to Hamiltonian Monte Carlo, arXiv (1)
- On Markov Chain Monte Carlo Methods for Tall Data, JMLR 2016 (I think?) (3)
- Firefly Monte Carlo: Exact MCMC with Subsets of Data, UAI 2014 (3)
- Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget, ICML 2014 (4)
- Towards Scaling up Markov Chain Monte Carlo: An Adaptive Subsampling Approach, ICML 2014 (4)
- Stochastic Gradient Hamiltonian Monte Carlo, ICML 2014 (2)
- Bayesian Learning via Stochastic Gradient Langevin Dynaimcs, ICML 2011 (4)
These don't quite fit in some of the other sections.
- Gradient Descent Converges to Minimizers, COLT 2016 (3)
- Dex-Net 1.0: A Cloud-Based Network of 3D Objects for Robust Grasp Planning Using a Multi-Armed Bandit Model with Correlated Rewards, ICRA 2016 (5)
- RRE: A Game-Theoretic Intrusion Response and Recovery Engine, IEEE Transactions on Parallel and Distributed Systems 2014 (4)