Deep-Learning-resources

MOOCS for Deeplearning

1. Deep learning specialization by Andrew Ng

Maths for Deep learning

1. The Matrix Calculus You Need For Deep Learning by Terence Parr and Jeremy Howard

Research papers for Deep Learning

1. AN ANALYSIS OF DEEP NEURAL NETWORK MODELS FOR PRACTICAL APPLICATIONS

Model-Free RL

Deep Q-Learning

Original Deep Q-Learning Paper (https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf)

Deep Recurrent Q-Learning (https://arxiv.org/abs/1507.06527)

Dueling Architectures (https://arxiv.org/abs/1511.06581)

Deep Double Q-Learning (https://arxiv.org/abs/1509.06461)

Prioritized Replay (https://arxiv.org/abs/1511.05952)

Rainbow (https://arxiv.org/abs/1710.02298)

Policy Gradients

A2C / A3C (https://arxiv.org/abs/1602.01783)

TRPO (https://arxiv.org/abs/1502.05477)

TRPO+GAE (https://arxiv.org/abs/1506.02438)

ACKTR (https://arxiv.org/abs/1708.05144)

PPO (https://arxiv.org/abs/1707.06347,

https://arxiv.org/abs/1707.02286)

ACER (https://arxiv.org/abs/1611.01224)

Soft Actor-Critic (https://arxiv.org/abs/1801.01290)

Deterministic Policy Gradients

Original DPG Paper (http://proceedings.mlr.press/v32/silver14.pdf)

DDPG (https://arxiv.org/abs/1509.02971)

TD3 (https://arxiv.org/abs/1802.09477)

Distributional RL

C51 (https://arxiv.org/abs/1707.06887)

QR-DQN (https://arxiv.org/abs/1710.10044)

IQN (https://arxiv.org/abs/1806.06923)

Dopamine (code library) (paper link, code link)

Policy Gradients with Action-Dependent Baselines

Q-Prop (https://arxiv.org/abs/1611.02247)

Stein Control Variates (https://arxiv.org/abs/1710.11198)

Mirage of Action-Dependent Baselines (https://arxiv.org/abs/1802.10031)

Path-Consistency Learning

Original PCL Paper (https://arxiv.org/abs/1702.08892)

Trust PCL (https://arxiv.org/abs/1707.01891)

Other Directions for Combining Policy Learning and Q-Learning

PGQ (https://arxiv.org/abs/1611.01626)

Reactor (https://arxiv.org/abs/1704.04651)

Interpolated Policy Gradients (this link is way too long)

Equivalence Between PG and SQL (https://arxiv.org/abs/1704.06440)

Evolution Algorithms

Evolutionary Strategies (https://arxiv.org/abs/1703.03864)

Exploration

Intrinsic Motivation

VIME (https://arxiv.org/abs/1605.09674)

Count-Based

Original pseudocounts paper (https://arxiv.org/abs/1606.01868)

Neural Density Models (https://arxiv.org/abs/1703.01310)

Hashing (https://arxiv.org/abs/1611.04717)

EX2 (https://arxiv.org/abs/1703.01260)

Self-Supervised Prediction (https://arxiv.org/abs/1705.05363)

Large-Scale Study of Curiosity (https://arxiv.org/abs/1808.04355)

Random Network Distillation (https://arxiv.org/abs/1810.12894)

Unsupervised RL

Variational Intrinsic Control (https://arxiv.org/abs/1611.07507)

Diversity is All You Need (https://arxiv.org/abs/1802.06070)

Variational Option Discovery Algorithms (https://arxiv.org/abs/1807.10299)

Transfer and Multitask RL

Progressive Networks (https://arxiv.org/abs/1606.04671)

Universal Value Function Approximators (http://proceedings.mlr.press/v37/schaul15.pdf)

RL + Unsupervised Auxiliary Tasks (https://arxiv.org/abs/1611.05397)

Intentional / Unintentional Agent (https://arxiv.org/abs/1707.03300)

PathNet (https://arxiv.org/abs/1701.08734)

Mutual Alignment Transfer Learning (https://arxiv.org/abs/1707.07907)

Learning an Embedding Space for Transfer (https://openreview.net/pdf?id=rk07ZXZRb)

Hindsight Experience Replay (https://arxiv.org/abs/1707.01495)

Hierarchy

Feudal Networks (https://arxiv.org/abs/1703.01161)

Strategic Attentive Writer (https://arxiv.org/abs/1606.04695)

Data-Efficient Hierarchical RL (https://arxiv.org/abs/1805.08296)

Fast Memory

Model-Free Episodic Control (https://arxiv.org/abs/1606.04460)

Neural Episodic Control (https://arxiv.org/abs/1703.01988)

Neural Map (https://arxiv.org/abs/1702.08360)

MERLIN (https://arxiv.org/abs/1803.10760)

Relational RNNs (https://arxiv.org/abs/1806.01822)

Model-Based

Learned Model

Imagination-Augmented Agents (https://arxiv.org/abs/1707.06203)

Model-Based Plus Model-Free Fine-tuning (https://arxiv.org/abs/1708.02596)

Model-Based Value Expansion (https://arxiv.org/abs/1803.00101)

Stochastic Ensemble Value Expansion (https://arxiv.org/abs/1807.01675)

Model Ensemble TRPO (hyperlink)

MB-MPO (https://arxiv.org/abs/1809.05214)

World Models (https://arxiv.org/abs/1809.01999)

Given Model

AlphaZero (https://arxiv.org/abs/1712.01815)

Expert Iteration (https://arxiv.org/abs/1705.08439)

Meta-RL

RL^2: Fast RL via Slow RL (https://arxiv.org/abs/1611.02779)

Learning to Reinforcement Learn (https://arxiv.org/abs/1611.05763)

MAML (https://arxiv.org/abs/1703.03400)

SNAIL (link to openreview)

Scaling RL

Accelerated Methods for Deep RL (https://arxiv.org/abs/1803.02811)

IMPALA (https://arxiv.org/abs/1802.01561)

Distributed Prioritized Experience Replay (https://openreview.net/forum?id=H1Dy---0Z)

R2D2 (https://openreview.net/forum?id=r1lyTjAqYX)

RLLib---Distributed RL with Ray (https://arxiv.org/abs/1712.09381)

RL in the Real World

Benchmarking Deep RL in the Real World (https://arxiv.org/abs/1809.07731)

Learning Dexterity (https://arxiv.org/abs/1808.00177)

QT-Opt (https://arxiv.org/abs/1806.10293)

Safety

Concrete Problems in AI Safety (https://arxiv.org/abs/1606.06565)

Learning from Human Preferences (https://arxiv.org/abs/1706.03741)

Constrained Policy Optimization (https://arxiv.org/abs/1705.10528)

Safe Exploration in Continuous Action Spaces (https://arxiv.org/abs/1801.08757)

Trial Without Error (https://arxiv.org/abs/1707.05173)

Leave No Trace (https://arxiv.org/abs/1711.06782)

Imitation Learning and Inverse Reinforcement Learning

MaxEnt IRL Thesis (link)

Guided Cost Learning (https://arxiv.org/abs/1603.00448)

GAIL (https://arxiv.org/abs/1606.03476)

DeepMimic (link)

VAIL (https://arxiv.org/abs/1810.00821)

One-Shot High-Fidelity Imitation Learning (https://arxiv.org/abs/1810.05017)

Other:

Unicorn: Continual Learning (https://arxiv.org/pdf/1802.08294.pdf)

Learning by Playing (https://arxiv.org/pdf/1802.10567.pdf)

Books of Deep learning

Dive into Deep Learning

Grokking Deep learning

Application

1. Google Colab Free GPU Tutorial

Useful Blogs on Deeplearning

1. Lessons Learned Reproducing a Deep Reinforcement Learning Paper