Chapter 16 – Deep Reinforcement Learning with Stable Baselines
- Stable Baselines is an improved implementation of OpenAI Baselines. Stable Baselines is a high-level library that is easier to use than OpenAI Baselines, and it also includes state-of-the-art deep RL algorithms along with offering several useful features.
- We can save the agent as
agent.save()and load the trained agent as
- We generally train our agent in a single environment per step but with Stable Baselines, we can train our agent in multiple environments per step. This helps our agent to learn quickly. Now, our states, actions, reward, and done will be in the form of a vector since we are training our agent in multiple environments. So, we call this a vectorized environment.
- In SubprocVecEnv, we run each environment in a different process, whereas in DummyVecEnv, we run each environment in the same process.
- With Stable Baselines, it is easier to view the computational...