machine learning

Protected: Online Convex Optimization (2) Complementing FTL Strategies with Regularization

Complementing the FTL strategy by introducing regularization techniques (L2 norm) in online prediction for digital transformation , artificial intelligence , and machine learning tasks.

2022.02.09

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Online Convex Optimization(1) FTL strategy and BTL supplement

Online Convex Optimization and FTL Strategies with Online Prediction for Digital Transformation , Artificial Intelligence , and Machine Learning Tasks with BTL Supplement

2022.02.08

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: New Developments in Reinforcement Learning (2) – Approaches Using Deep Learning

On seven methods for improving deep reinforcement learning used in digital transformation , artificial intelligence , and machine learning tasks (first generation DQN, dual Q learning (dual DQN method), prioritized experience replay, collision Q networks, distributed reinforcement learning (categorical DQN method) noise networks, n-step cutting returns) and alpha zero

2022.02.07

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Protected: New Developments in Reinforcement Learning (1) – Reinforcement Learning with Risk Indicators

Different approaches (regular process TD learning, RDPS methods) and implementations (Monte Carlo, analytical methods) in risk-aware reinforcement learning methods for digital transformation , artificial intelligence , and machine learning tasks.

2022.02.03

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Protected: Partially Observed Markov Decision Processes (2) Planning POMDPs

Reinforcement learning for digital transformation , artificial intelligence , and machine learning tasks; obtaining optimal strategies using partial observation Markov decision process planning methods.

2022.02.02

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Protected: Partially Observed Markov Decision Processes (1) On POMDPs and Belief MDPs

Belief MDPs, more flexible reinforcement learning using partially observed Markov decision processes (POMDPs) for digital transformation , artificial intelligence , and machine learning tasks.

2022.02.01

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Reinforcement Learning with Function Approximation (2) – Function Approximation of Value Functions (For Online Learning)

Theory of function approximation online methods gradient TD learning, least-squares based least-squares TD learning (LSTD), GTD2)for reinforcement learning with a huge number of states used in digital transformation , artificial intelligence , and machine learning tasks, and regularization with LASSO.

2022.01.28

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Protected: Reinforcement Learning with Function Approximation (1) – Function Approximation of Value Functions (Batch Learning Case)

Function approximation in the case of batch learning of value functions to deal with a huge number of states in reinforcement learning for digital transformation, artificial intelligence, and machine learning tasks.

2022.01.26

強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Model-based reinforcement learning(Sparse sampling, UCT, Monte Carlo search tree)

Model-based reinforcement learning (sparse sampling, UCT, Monte Carlo search trees) used for digital transformation artificial intelligence , and machine learning tasks.

2022.01.24

IOT技術:IOT TechnologyStream Data Processingオンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Model-free reinforcement learning (2) – Method iteration (Q-learning, SARSA, Actor-click method)

Value iteration methods Q-learning, SARSA, Actor-critic methods to model-free reinforcement learning for digital transformation , artificial intelligence and machine learning tasks.

2022.01.21

IOT技術:IOT TechnologyStream Data Processingオンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics