Tensor Action Spaces for Multi-agent Robot Transfer Learning
Devin Schwab,Yifeng Zhu,Manuela Veloso,Devin Schwab,Yifeng Zhu,Manuela Veloso
We explore using reinforcement learning on single and multi-agent systems such that after learning is finished we can apply a policy zero-shot to new environment sizes, as well as different number of agents and entities. Building off previous work, we show how to map back and forth between the state and action space of a standard Markov Decision Process (MDP) and multi-dimensional tensors such tha...
