10 results found Sort:

allenai
reward-bench allenai
65
557
apache-2.0
6
RewardBench: the first evaluation tool for reward models.
rlhf preference-learning
Created 2023-12-23
219 commits to main branch, last one about a month ago
tournesol-app
tournesol tournesol-app
50
348
other
10
Free and open source code of the https://tournesol.app platform. Meet the community on Discord https://discord.gg/WvcSG55Bf3
django python dataset reactjs youtube ai-ethics social-choice bradley-terry-model preference-learning django-rest-framework recommendation-engine preference-aggregation golden-ratio-optimization
Created 2021-03-23
1,654 commits to main branch, last one 5 days ago
IAAR-Shanghai
ICSFSurvey IAAR-Shanghai
5
166
unknown
4
Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.
decoding reasoning self-refine self-correct hallucination self-feedback attention-head self-correction chain-of-thought self-consistency self-improvement data-augmentation preference-learning internal-consistency large-language-model large-language-models knowledge-distillation
Created 2024-06-01
36 commits to master branch, last one 4 months ago
qxcv
magical qxcv
11
77
isc
6
The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)
imitation-learning preference-learning reinforcement-learning reinforcement-learning-environments
Created 2019-11-12
144 commits to pyglet1.5 branch, last one 3 years ago
SMARTlab-Purdue
SAN-NaviSTAR SMARTlab-Purdue
5
55
mit
4
This repository contains the source code for our paper: "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning". For more details, please refe...
transformer machine-learning robot-navigation preference-learning reinforcement-learning socially-aware-navigation
Created 2023-04-20
38 commits to master branch, last one about a month ago
JanoschMenke
metis JanoschMenke
12
49
mit
1
Python-based GUI to collect Feedback of Chemist in Molecules
generative-ai drug-discovery machine-learning human-in-the-loop de-novo-drug-design preference-learning
Created 2024-04-29
31 commits to main branch, last one 7 months ago
sail-sg
dice sail-sg
3
43
mit
3
Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
rlhf alignment preference-learning large-language-models
Created 2024-06-12
7 commits to main branch, last one 8 days ago
gao-g
prelude gao-g
1
37
mit
2
Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".
llm gpt4 llms edits alignment transformers user-feedback human-feedback interpretability preference-learning
Created 2024-04-25
15 commits to main branch, last one 5 months ago
liushunyu
awesome-direct-preference-optimization liushunyu
0
35
unknown
1
A Survey of Direct Preference Optimization (DPO)
dpo llm llms review survey alignment preference-learning large-language-model large-language-models direct-preference-optimization reinforcement-learning-from-human-feedback
Created 2024-11-26
52 commits to main branch, last one about a month ago
CJReinforce
RIME_ICML2024 CJReinforce
2
28
mit
2
Official code for ICML 2024 paper, "RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences" (ICML 2024 Spotlight)
robotics locomotion manipulation deep-learning preference-learning reinforcement-learning artificial-intelligence reinforcement-learning-from-human-feedback
Created 2024-04-04
17 commits to main branch, last one 6 months ago