https://github.com/jeffasante/grpo-maze-solver
A reinforcement learning agent that learns to solve mazes using Group Relative Policy Optimization (GRPO).
https://github.com/jeffasante/grpo-maze-solver
deep-seek-r1-grpo group-relative-policy-optimization reinforcement-learning-agent
Last synced: 4 months ago
JSON representation
A reinforcement learning agent that learns to solve mazes using Group Relative Policy Optimization (GRPO).
- Host: GitHub
- URL: https://github.com/jeffasante/grpo-maze-solver
- Owner: jeffasante
- License: mit
- Created: 2025-02-08T13:48:59.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2025-02-08T16:29:41.000Z (over 1 year ago)
- Last Synced: 2025-02-08T16:33:31.784Z (over 1 year ago)
- Topics: deep-seek-r1-grpo, group-relative-policy-optimization, reinforcement-learning-agent
- Language: Python
- Homepage:
- Size: 2.93 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0