This document is a glossary for core concepts of TorchRL framework.
Environment is the system which provides feedback to the Agent. Currently, Open AI gym.Env environments are being used. The system is flexible enough to extend to any other environment kind.
Any task is defined by extending the abstract class
Problem. A problem’s entrypoint
run() which generates
the trajectory rollout and call’s the Agent’s
learn() method with
appropriate rollout information.
HParams set is a class of arbitrary
key-value pairs that contain the hyper-parameters for the problem. Keeping
these as first-class objects in the code base allow for easily reproducible