Hacker News new | ask | show | jobs
user: AMavorParker
created: 2018-10-02
karma: 21

submissions:

Propel: Breaking the Solver Bottleneck in Task-Generator RL
3 points | 0 comments
Unix-CTF: Procedural Environments for Unix-Competence Reinforcement Learning
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self- Play
51 points | 6 comments