# Duck Hunt Openenv

- **Event:** [WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80)
- **When:** Jan 31 at 9:00 AM – Feb 1 at 5:00 PM (PST)
- **Where:** 400 California St, San Francisco, CA
- **Team:** [David Mayboroda](https://cerebralvalley.ai/u/davidmayboroda)
- **GitHub:** https://github.com/dmayboroda/horizon_min
- **Demo video:** https://youtu.be/bV8oiVYLhgs
- **Gallery:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/42

OpenEnv for thr VLM to play Duck Hunt game, ready for GRPO training and eval

Part of research that called:
Hardware-Aware Horizon Minimization for VLM Game Agents
Training Vision-Language Models to Play Duck Hunt with Adaptive Latency Compensation

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/42. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt