深層学習:Deep Learning

Protected: Implementation of two approaches to improve environmental awareness, a weak point of deep reinforcement learning.

Implementation of two approaches to improve environment awareness, a weakness of deep reinforcement learning used in digital transformation, artificial intelligence, and machine learning tasks (inverse predictive, constrained, representation learning, imitation learning, reconstruction, predictive, WorldModels, transition function, reward function Weaknesses of representation learning, VAE, Vision Model, RNN, Memory RNN, Monte Carlo methods, TD Search, Monte Carlo Tree Search, Model-based learning, Dyna, Deep Reinforcement Learning)

2023.04.27

アルゴリズム:Algorithmsグラフ理論スパースモデリングマルチエージェントシステム幾何学:Geometry強化学習微分積分:Calculus数理論理学:Mathematical logic最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Protected: Overview of Weaknesses and Countermeasures in Deep Reinforcement Learning and Two Approaches to Improve Environment Recognition

An overview of the weaknesses and countermeasures of deep reinforcement learning utilized in digital transformation, artificial intelligence, and machine learning tasks and two approaches of improving environmental awareness Mixture Density Network, RNN, Variational Auto Encoder, World Modles, Expression Learning, Strategy Network Compression, Model Free Learning, Sample-Based Planning Model, Dyna, Simulation-Based, Sample-Based, Gaussian Process, Neural Network, Transition Function, Reward Function) World Modles, Representation Learning, Strategy Network Compression, Model-Free Learning, Sample-Based Planning Model, Dyna, Simulation-Based, Sample-Based, Gaussian Process, Neural Network, Transition Function, Reward Function, Simulator , learning capability, transition capability

2023.04.13

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra

Protected: Value Assessment and Policy and Weaknesses in Deep Reinforcement Learning

Value assessment and strategies and weaknesses in deep reinforcement learning used for digital transformation, artificial intelligence, and machine learning tasks poor sample efficiency, difficulty in validating methods as well, impact of implementation practices on performance, library initial values, poor reproducibility, over-training, local optimum, dexterity, TRPO, PPO, continuous value control, image control, policy-based, value-based

2023.03.30

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra

Protected: TRPO/PPO and DPG/DDPG, an improvement of the Policy Gradient method of reinforcement learning

TRPO/PPO and DPG/DDPG (Pendulum, Actor Critic, SequentialMemory, SequentialMemory, and SequentialMemory), which are improvements of Policy Gradient methods of reinforcement learning used for digital transformation, artificial intelligence, and machine learning tasks. Adam, keras-rl, TD error, Deep Deterministic Policy Gradient, Deterministic Policy Gradient, Advanced Actor Critic, A2C, A3C, Proximal Policy Optimization, Trust Region Policy Optimization, Python)

2023.03.16

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra

Protected: Applying Neural Networks to Reinforcement Learning Applying Deep Learning to Strategy:Advanced Actor Critic (A2C)

Application of Neural Networks to Reinforcement Learning for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Implementation of Advanced Actor Critic (A2C) applying deep learning to strategies (Policy Gradient method, Q-learning, Gumbel Max Trix, A3C (Asynchronous Advantage Actor Critic))

2023.03.02

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra

Theory and algorithms of various reinforcement learning techniques and their implementation in python

Theory and algorithms of various reinforcement learning techniques used for digital transformation, artificial intelligence, and machine learning tasks and their implementation in python reinforcement learning,online learning,online prediction,deep learning,python,algorithm,theory,implementation

2023.02.05

アルゴリズム:Algorithmsオンライン学習グラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra

Protected: Applying Neural Networks to Reinforcement Learning Deep Q-Network Applying Deep Learning to Value Assessment

Application of Neural Networks to Reinforcement Learning for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Deep Q-Network Prioritized Replay, Multi-step applying deep learning to value assessment Deep Q-Network applying deep learning to value assessment (Prioritized Replay, Multi-step Learning, Distibutional RL, Noisy Nets, Double DQN, Dueling Network, Rainbow, GPU, Epsilon-Greedy method, Optimizer, Reward Clipping, Fixed Target Q-Network, Experience Replay, Average Experience Replay, Mean Square Error, Mean Squared Error, TD Error, PyGame Learning Enviroment, PLE, OpenAI Gym, CNN

2023.02.02

pythonアルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra集合論:Set theory

Protected: Gauss-Newton and natural gradient methods as continuous optimization for machine learning

Gauss-Newton and natural gradient methods as continuous machine learning optimization for digital transformation, artificial intelligence, and machine learning tasks Sherman-Morrison formula, one rank update, Fisher information matrix, regularity condition, estimation error, online learning, natural gradient method, Newton method, search direction, steepest descent method, statistical asymptotic theory, parameter space, geometric structure, Hesse matrix, positive definiteness, Hellinger distance, Schwarz inequality, Euclidean distance, statistics, Levenberg-Merkert method, Gauss-Newton method, Wolf condition

2023.01.24

アルゴリズム:Algorithms幾何学:Geometry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線形代数:Linear Algebra

Protected: Application of Neural Networks to Reinforcement Learning Value Function Approximation, which implements value evaluation as a function with parameters.

Application of Neural Networks to Reinforcement Learning used for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Examples of implementing value evaluation with functions with parameters (CartPole, Q-table, TD error, parameter update, Q-Learning, MLPRegressor, Python)

2023.01.19

アルゴリズム:Algorithmsグラフ理論幾何学:Geometry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線形代数:Linear Algebra

Protected: Application of Neural Networks to Reinforcement Learning (2) Basic Framework Implementation

Implementation of a basic framework for reinforcement learning with neural networks utilized for digital transformation, artificial intelligence and machine learning tasks (TensorBoard, Image tab, graphical, real-time, progress check, wrapper for env. Observer, Trainer, Logger, Agent, Experience Replay, episode, action probability, policy, Epsilon-Greedy method, python)

2023.01.04

アルゴリズム:Algorithms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線形代数:Linear Algebra