A diffusion RL method with height maps and diffusion actor network packs more items on average than prior DRL approaches in online 3D bin packing.
A dynamic multi-modal deep reinforcement learn- ing framework for 3 d BPP
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization
A diffusion RL method with height maps and diffusion actor network packs more items on average than prior DRL approaches in online 3D bin packing.