Published inTowards Data ScienceUnderstanding and Implementing Distributed Prioritized Experience Replay (Horgan et al., 2018)Accelerating Deep Reinforcement Learning with Distributed ArchitecturesNov 25, 2019Nov 25, 2019
Published inTowards Data ScienceIn-depth review of Soft Actor-CriticUnderstanding State-of-the-Art Reinforcement Learning AlgorithmsNov 24, 20193Nov 24, 20193
Published inTowards Data ScienceDueling Deep Q NetworksDueling Network Architectures for Deep Reinforcement LearningOct 19, 20193Oct 19, 20193
Published inTowards Data ScienceDouble Deep Q NetworksTackling maximization bias in Deep Q-learningJul 17, 20195Jul 17, 20195
Published inTowards Data ScienceVanilla Deep Q NetworksDeep Q Learning ExplainedJul 15, 20192Jul 15, 20192
Published inTowards Data ScienceDeep Deterministic Policy Gradients ExplainedReinforcement Learning in Continuous Action SpacesMar 20, 201910Mar 20, 201910
Published inTowards Data ScienceCan Artificial Intelligence Help Medical Decision Making?A Reinforcement Learning based Intelligent Physician for Chemotherapy TreatmentMar 19, 2019Mar 19, 2019
Published inTowards Data ScienceUnderstanding Actor Critic MethodsPreliminariesFeb 6, 201941Feb 6, 201941
Deriving Policy Gradients and Implementing REINFORCEPolicy gradient methods are ubiquitous in model free reinforcement learning algorithms — they appear frequently in reinforcement learning…Dec 30, 201820Dec 30, 201820
