Training Language Models to Follow Instructions with Human Feedback
Established the instruction tuning and RLHF recipe used by InstructGPT.
- from
- Artificial Intelligence
- added
- 2026-10-10
- likes
- 0
similar
-
trl github.com
Train transformer language models with reinforcement learning.
-
Language learning with NLP and reinforcement learning blog.dennybritz.com
-
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL proceedings.mlr.press
ICML'21, 2021. [All Versions]. [Project].
-
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following arxiv.org
ICLR'19, 2019. [All Versions].
-
Learning to Perform Physics Experiments via Deep Reinforcement Learning openreview.net
ICLR'17, 2017. [All Versions].
-
RLlib ray.readthedocs.io
Scalable Reinforcement Learning.
Artificial Intelligence › Learn > Foundational papers: “Established the instruction tuning and RLHF recipe used by InstructGPT.”