In the previous chapter, we looked at several promising learning environments that you can use to train agents to solve a variety of different tasks. In Chapter 7, Creating Custom OpenAI Gym Environments – CARLA Driving Simulator, we also saw how you can create your own environments to solve the task or problem that you may be interested in developing a solution for, using intelligent and autonomous software agents. That provides you with directions on where you can head after finishing in order to explore and play around with all the environments, tasks, and problems we discussed in this book. Along the same lines, in this chapter, ...
Exploring the Learning Algorithm Landscape - DDPG (Actor-Critic), PPO (Policy-Gradient), Rainbow (Value-Based)
Get Hands-On Intelligent Agents with OpenAI Gym now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
