- conda create --name universe python=3.6 anaconda
- With Docker, we can pack our application with its dependencies, which is called container, and we can simply run our applications on the server without using any external dependency with our packed Docker container.
- gym.make(env_name)
- from gym import envs
print(envs.registry.all()) - OpenAI Universe is an extension of OpenAI Gym and it also provides various rich environments.
- Placeholder is used for feeding external data whereas variable is used for holding values.
- Everything in TensorFlow will be represented as a computational graph that consists of nodes and edges, where nodes are the mathematical operations, say addition, multiplication and so on, and edges are the tensors.
- Computation graphs will only be defined; in order to execute the computation graph, we use TensorFlow sessions.