Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Game On: Integrating RL Agents with Environments

via CodeSignal

Go to class Write review

Overview

In this course, we integrate the grid-world environment with a Q-learning agent, focusing on agent-environment interaction and training over multiple episodes. We explore the exploration vs. exploitation tradeoff using an ε-greedy strategy and visualize performance through reward plots and policy displays.

Syllabus

  • Unit 1: Integrating Agents with Environments in Reinforcement Learning
    • Agent-Environment Interaction Loop Integration
    • Evaluating Agent Performance Over Time
    • Fix the Q-Learning Bug
    • Visualize Your Agent in Action
    • Integrate Agent with Environment
  • Unit 2: Balancing Exploration and Exploitation with Epsilon-Greedy Strategy
    • Epsilon Greedy Strategy in Action
    • Epsilon-Greedy Strategy Implementation
    • Fix the Epsilon-Greedy Bug
    • Epsilon Decay for Smarter Learning
    • Epsilon-Greedy Strategy Implementation
  • Unit 3: Visualizing Training Statistics in Reinforcement Learning
    • Visualize Learning with Moving Averages
    • Visualize Learning with Reward Plots
    • Visualize Agent Learning Progress
    • Streamline Your Visualization Code
  • Unit 4: Visualizing Policies and Value Functions in Reinforcement Learning
    • Visualizing Agent's Decision Strategy
    • Fix the State Value Bug
    • Visualize Agent's Value Function
    • Visualize Policy and Value Together
    • Integrate and Visualize Learning Agent

Reviews

Start your review of Game On: Integrating RL Agents with Environments

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.