A framework for training larger networks for deep Reinforcement learning
Kei Ota, Devesh K. Jha, Asako Kanezaki
De quem é
- Mitsubishi Electric Research Laboratoriesafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- Interactive Planning Using Large Language Models for Partially Observable Robotic TasksMitsubishi Electric Research Laboratories · 77 citações
- Continuous-time successive convexification for constrained trajectory optimizationMitsubishi Electric Research Laboratories · 70 citações
- RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization With Knowledge-Infused Reinforcement LearningMitsubishi Electric Research Laboratories · 67 citações
- TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and EnhancementMitsubishi Electric Research Laboratories · 66 citações
- Real-Time Mixed-Integer Quadratic Programming for Vehicle Decision-Making and Motion PlanningMitsubishi Electric Research Laboratories · 65 citações
- TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion ModelsMitsubishi Electric Research Laboratories · 53 citações