How can we guarantee that every action of each state is chosen? And why is that so important? We will first answer the latter question, and then show how we can (at least in theory) explore the environment to reach every possible state.
- Title Page
- Copyright and Credits
- Dedication
- About Packt
- Contributors
- Preface
- Section 1: Algorithms and Environments
- The Landscape of Reinforcement Learning
- Implementing RL Cycle and OpenAI Gym
- Solving Problems with Dynamic Programming
- Section 2: Model-Free RL Algorithms
- Q-Learning and SARSA Applications
- Deep Q-Network
- Learning Stochastic and PG Optimization
- TRPO and PPO Implementation
- DDPG and TD3 Applications
- Section 3: Beyond Model-Free Algorithms and Improvements
- Model-Based RL
- Imitation Learning with the DAgger Algorithm
- Understanding Black-Box Optimization Algorithms
- Developing the ESBAS Algorithm
- Practical Implementation for Resolving RL Challenges
- Assessments
- Other Books You May Enjoy
The exploration problem
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.