This paper examines new forms of collaboration between producers and consumers that are emerging in the digital entertainment space. Taking the case of the video-game industry, we...
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
Multi-agent decision problems, in which independent agents have to agree on a joint plan of action or allocation of resources, are central to AI. In such situations, agents' ...
Reshef Meir, Maria Polukarov, Jeffrey S. Rosensche...
— This paper shows that the distributed representation found in Learning Vector Quantization (LVQ) enables reinforcement learning methods to cope with a large decision search spa...
Recent research in multi-robot exploration and mapping has focused on sampling environmental fields, which are typically modeled using the Gaussian process (GP). Existing informa...