policy
Deep-Q-Network-for-Continuous-Maze-Navigation
joshith-allen · PyTorch
or hover any field below to flag it
Overview
Name
Deep-Q-Network-for-Continuous-Maze-Navigation
Author
joshith-allen
Framework
PyTorch
License
MIT
Skill type
navigation
Evidence level
untested
Task description
Train a reinforcement learning agent using the Deep Q-Network (DQN) algorithm for continuous maze navigation. The agent interacts with a custom environment, receives rewards and penalties based on its actions, and gradually learns an optimal policy for reaching the target while avoiding hazards and
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 yetCompatible environments
0No environments list Deep-Q-Network-for-Continuous-Maze-Navigation yet.
Datasets that reference this policy
0No datasets reference Deep-Q-Network-for-Continuous-Maze-Navigation yet.