policy

micro-coder-rl-sandbox

jeffjaehoyang · PyTorch

or hover any field below to flag it

Overview

Name
micro-coder-rl-sandbox
Author
jeffjaehoyang
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
An experimental, small-scale RL framework designed to profile and optimize the execution latency of verifiable reward functions. This project implements a RL training loop for a 1.5B parameter coding model, specifically targeting the "Evaluation Bottleneck" where standard containerization (Docker) t

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list micro-coder-rl-sandbox yet.

Datasets that reference this policy

0

No datasets reference micro-coder-rl-sandbox yet.