policy
Snack-RL
Horese07 · PyTorch
or hover any field below to flag it
Overview
Name
Snack-RL
Author
Horese07
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
A small reinforcement learning project that trains an agent to play Snake. The repository contains game logic, an RL agent and model code, a replay buffer implementation, utilities, and a script to play the game as a human. A training progress image is included to show example training results.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
20realmanrobot-hand-eye-calibrationnot in seedmasterhow-oneoccnot in seedsergionr2-racingrobotnot in seedgabrielnhn-ros2-line-followernot in seedvivek1795-gesture-controlled-robotic-arm-in-mujoconot in seedlogesh1516-mycobot-280jn-descriptionnot in seedcrm-uam-visionracenot in seeddavide-ciraolo-fischertechnik-3d-robot-webcam-gestures-systemnot in seedbobbycephy-robot-gripper-cameranot in seedsamyukamtam-hexapodnot in seedtx-leo-camera-calibration-handeye-calibrationnot in seedflexiv-camera-modulenot in seeddavidea97-multi-camera-hand-eye-calibrationnot in seedrensauce-3ugersip-group3not in seedfpj-gaoge-finsrov-an-underwater-camera-based-multi-robot-platformnot in seedsallu-786-ros2-mcp-web-portalnot in seedsiddhant-135-sacrid-vision-pipelinenot in seeddobot-vx500-smart-cameranot in seedargymats-thesis-delta-robotnot in seedislamahmedes43-gochase2not in seed
Compatible environments
0No environments list Snack-RL yet.
Datasets that reference this policy
0No datasets reference Snack-RL yet.