policy
GridDQN
Thiruvel-AP · PyTorch
or hover any field below to flag it
Overview
Name
GridDQN
Author
Thiruvel-AP
Framework
PyTorch
License
unknown
Skill type
navigation
Evidence level
untested
Task description
This project is to train an agent in a custom grid world with Deep Q-Network (DQN) from scratch. The agent learns optimal paths via reward-driven exploration and converges to a stable policy for shortest-path navigation.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
0+20 mentioned but not in catalog yetNo robots list GridDQN as compatible yet. Know of one? Flag it above.
Compatible environments
0No environments list GridDQN yet.
Datasets that reference this policy
0No datasets reference GridDQN yet.