policy

dyna-maze

thehawkgriffith · PyTorch

or hover any field below to flag it

Overview

Name
dyna-maze
Author
thehawkgriffith
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
An agent designed by the dyna-Q approach of simultaneous Direct RL and Model Learning as described in the book "An Introduction to Reinforcement Learning, Sutton et al. 2018" The environment used is almost exactly the same as described in the book with the exception of a small negative living rewar

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list dyna-maze yet.

Datasets that reference this policy

0

No datasets reference dyna-maze yet.