search

allenai / RL4LMs

A modular RL library to fine-tune language models to human preferences
https://rl4lms.apps.allenai.org/
Apache License 2.0
2.18k stars 191 forks source link

fix: OnPolicyAlgorithm doesnot have the parameter: create_eval_env #36

Open hscspring opened 1 year ago

hscspring commented 1 year ago

  1. OnPolicyAlgorithm doesnot have the parameter: create_eval_env

  2. It's better to assign dtype in DictSpace of TextGenEnv explicitly

gangancuicuia commented 1 week ago

你好 请问解决了吗

hscspring commented 1 week ago

按pr操作即可

gangancuicuia @.***> 于2024年9月22日周日 12:23写道：

你好 请问解决了吗

— Reply to this email directly, view it on GitHub https://github.com/allenai/RL4LMs/pull/36#issuecomment-2365457361, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABZDQ4MQSOR4QKQVW5XXMG3ZXZA4ZAVCNFSM6AAAAABOUGALKOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNRVGQ2TOMZWGE . You are receiving this because you authored the thread.Message ID: @.***>