dpf
Joined 13 years ago
Karma
341
Submissions
14
Member since
Jul 1
Recent submissions
Comment · 3 years ago
code-davinci-002 is a base LM, and the other 3.5 models (text-davinci-{002,003}, gpt-3.5-turbo, and ChatGPT) use instruction tuning and/or RLHF. Source: https://platform.openai.com/docs/model-index-for-researchers
Comment · 8 years ago
Previous discussion:
Comment · 9 years ago
These environments are often used as a testbed for reinforcement learning, e.g. https://arxiv.org/abs/1502.05477