policy

Q-Learning

mohamedmansour0 · PyTorch

or hover any field below to flag it

Overview

Name
Q-Learning
Author
mohamedmansour0
Framework
PyTorch
License
unknown
Skill type
navigation
Evidence level
untested
Task description
The model-free reinforcement learning techniques as the Q-learning algorithm can be successful with relatively small training episodes in learning how to navigate independently, it converged 80% of the time after only 25,000 training episodes. The high complexity of the algorithm may restrict the tr

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 Q-Learning yet.

Datasets that reference this policy

0

No datasets reference Q-Learning yet.