3rd Place
Lambda
ShopRLVE-GYM HF Blog https://huggingface.co/blog/thebajajra/shop-rlve-gym
Core trick
Trains shopping agents in a gym whose rewards are computed from verifiable environment state rather than from a judge model.
Tags
Description
ShopRLVE-GYM HF Blog
https://huggingface.co/blog/thebajajra/shop-rlve-gym
README excerpt
# EcomRLVE-Gym Team LAMBDA submission for Hackathon 2026