HNHacker News
TopNewBestAskShowJobs

AMavorParker

21 karma · joined October 2, 2018

submissionscomments

Propel: Breaking the Solver Bottleneck in Task-Generator RL

vmax.ai·3 pts·AMavorParker·
0

Unix-CTF: Procedural Environments for Unix-Competence Reinforcement Learning

twitter.com·2 pts·AMavorParker·
0

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self- Play

vmax.ai·51 pts·AMavorParker·
6