RL-based co-training in RLinf
AI & ML interests
None defined yet.
Recent Activity
Papers
RLinf-Co: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
-
RLinf/RLinf-OpenVLAOFT-LIBERO-130-Base-Lora
Reinforcement Learning • 8B • Updated • 1.16k -
RLinf/RLinf-OpenVLAOFT-ManiSkill-Base-Main
8B • Updated • 484 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 40 -
RLinf/RLinf-OpenVLAOFT-LIBERO-130
Reinforcement Learning • 8B • Updated • 102 • 2
RL-based co-training in RLinf
-
RLinf/RLinf-OpenVLAOFT-LIBERO-130-Base-Lora
Reinforcement Learning • 8B • Updated • 1.16k -
RLinf/RLinf-OpenVLAOFT-ManiSkill-Base-Main
8B • Updated • 484 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 40 -
RLinf/RLinf-OpenVLAOFT-LIBERO-130
Reinforcement Learning • 8B • Updated • 102 • 2