Arthur JulianiSimple Reinforcement Learning with Tensorflow Part 7: Action-Selection Strategies for ExplorationIn this entry of my RL series I would like to focus on the role that exploration plays in an agent’s behavior. I will go over a few of the…Nov 14, 201614Nov 14, 201614
Carsten FriedrichPart 4 - Neural Network Q Learning, a Tic Tac Toe player that learns - kind ofTraining a Neural Network to learn the Tic Tac Toe Q functionJun 6, 20182Jun 6, 20182
Jonathan HuiRL — DQN Deep Q-networkCan computers play video games like a human? In 2015, DQN beat human experts in many Atari games. But once comes to complex war strategy…Jul 16, 20189Jul 16, 20189
ODSC - Open Data ScienceReinforcement Learning vs. Differentiable ProgrammingWe’ve discussed the idea of differentiable programming, where we incorporate existing programs into deep learning models. But if you’re a…Apr 16, 20194Apr 16, 20194
Arthur JulianiMaximum Entropy Policies in Reinforcement Learning & Everyday LifeAs those who follow this blog are probably aware, I spend a lot of time thinking about Reinforcement Learning (RL). These thoughts…Nov 2, 201812Nov 2, 201812
Jonathan HuiRL — LQR & iLQR Linear Quadratic RegulatorReinforcement learning can be divided into Model-free and Model-based learning. Model-free learning emphasizes heavily on sampling. It…Sep 19, 20187Sep 19, 20187
InTDS ArchivebyAdrien Lucas EcoffetPaper repro: Deep Metalearning using “MAML” and “Reptile”How do you learn from very little data? Two recent papers may have the answer. Let’s reproduce them!Apr 2, 20189Apr 2, 20189
Roman RingDeep Reinforcement Learning with TensorFlow 2.0In this tutorial I will showcase the upcoming TensorFlow 2.0 features through the lense of deep reinforcement learning (DRL) by…Jan 19, 20193Jan 19, 20193
Jonathan HuiRL — Meta-LearningSo far, AI cannot learn as efficiently as a human. Many classifiers take millions of training samples to train and knowledge is not shared…Apr 25, 20183Apr 25, 20183
InHuggingFacebyThomas Wolf🐣 From zero to research — An introduction to Meta-learningMeta-learning is an exciting trend of research in the machine-learning community which tackles the problem of learning to learn.Apr 3, 201811Apr 3, 201811
InTDS ArchivebyYash PatelReinforcement Learning w/ Keras + OpenAI: Actor-Critic ModelsQuick RecapJul 31, 201725Jul 31, 201725
InTensorFlowbyTensorFlowDeep Reinforcement Learning: Playing CartPole through Asynchronous Advantage Actor Critic (A3C)…By Raymond Yuan, Software Engineering InternJul 31, 20186Jul 31, 20186
InTDS ArchivebyVaishak V.KumarSoft Actor-Critic DemystifiedAn intuitive explanation of the theory and a PyTorch implementation guideJan 8, 201915Jan 8, 201915
InTDS ArchivebyMauricio Fadel Argerich5 Frameworks for Reinforcement Learning on PythonProgramming your own Reinforcement Learning implementation from scratch can be a lot of work, but you don’t need to do that. There are…Jun 4, 20206Jun 4, 20206
Jonathan HuiRL — Inverse Reinforcement LearningIt is a major challenge for reinforcement learning (RL) to process sparse and long-delayed rewards. It is difficult to untangle irrelevant…Jan 29, 20204Jan 29, 20204
