6 papers
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
MiniMax, :, Aili Chen +219
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
Unsupervised Skill Discovery through Skill Regions Differentiation
Ting Xiao, Jiakun Zheng, Rushuai Yang +4
Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based…
Online Preference Alignment for Language Models via Count-based Exploration
Chenjia Bai, Yang Zhang, Shuang Qiu +3
Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform pr…
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Jiafei Lyu, Kang Xu, Jiacheng Xu +6
We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-…
Constrained Ensemble Exploration for Unsupervised Skill Discovery
Chenjia Bai, Rushuai Yang, Qiaosheng Zhang +4
Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly condu…
Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
Xiaoyu Wen, Chenjia Bai, Kang Xu +4
Cross-domain offline reinforcement learning leverages source domain data with diverse transition dynamics to alleviate the data requirement for the target domain. However, simply m…