•Reinforcement Learning Techniques with R
•The Course Overview
•Understanding the RL Grid World Problem
•Implementing the Grid World Framework in R
•Navigating Grid World and Calculating Likely Successful Outcomes
•R Example Finding Optimal Policy Navigating x Grid
•R Example Updating Optimal Policy Navigating x Grid
•R Example MDPtoolbox Solution Navigating x Grid
•More MDPtoolbox Function Examples Using R
•R Example Finding Optimal x Grid World Policy
•R Exercise Building a x Grid World Environment
•R Exercise Solution Building a x Grid World Environment
•Practical Reinforcement Learning Agents and Environments
•Install RStudio
•Install Python
•Launch Jupyter Notebook
•Learning Type Distinctions
•Get Started with Reinforcement Learning
•Realworld Reinforcement Learning Examples
•Key Terms in Reinforcement Learning
•OpenAI Gym
•Monte Carlo Method
•Monte Carlo Method in Python
•Monte Carlo Method in R
•Practical Reinforcement Learning in OpenAI Gym
•Markov Decision Process Concepts
•Python MDP Toolbox
•Value and Policy Iteration in Python
•MDP Toolbox in R
•Value Iteration and Policy Iteration in R
•Temporal Difference Learning
•Temporal Difference Learning in Python
•Temporal Difference Learning in R
•Discover Algorithms for RewardBased Learning in R
•R Example Building ModelFree Environment
•R Example Finding ModelFree Policy
•R Example Finding ModelFree Policy Continued
•R Example Validating ModelFree Policy
•Policy Evaluation and Iteration
•R Example Moving a Pawn with Changed Parameters
•Discount Factor and Policy Improvement
•Monte Carlo Methods
•Environment and QLearning Functions with R
•Learning Episode and StateAction Functions in R
•StateActionRewardStateAction SARSA
•Simulated Annealing An Alternative to QLearning
•QLearning with a Discount Factor
•Visual QLearning Examples
•Understanding the RL “Grid World” Problem
•R Example – Finding Optimal Policy Navigating 2 x 2 Grid
•R Example – Updating Optimal Policy Navigating 2 x 2 Grid
•R Example – MDPtoolbox Solution Navigating 2 x 2 Grid
•R Example – Finding Optimal 3 x 4 Grid World Policy
•R Exercise – Building a 3 x 4 Grid World Environment
•R Exercise Solution – Building a 3 x 4 Grid World Environment
•Practical Reinforcement Learning – Agents and Environments
•Real-world Reinforcement Learning Examples
•Discover Algorithms for Reward-Based Learning in R
•R Example – Building Model-Free Environment
•R Example – Finding Model-Free Policy
•R Example – Finding Model-Free Policy (Continued)
•R Example – Validating Model-Free Policy
•R Example – Moving a Pawn with Changed Parameters
•Environment and Q-Learning Functions with R
•Learning Episode and State-Action Functions in R
•State-Action-Reward-State-Action (SARSA)
•Simulated Annealing – An Alternative to Q-Learning
•Q-Learning with a Discount Factor
•