Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algorithms in a network of agents. The framework defines an organizational structure for automated supervision and a communication protocol for exchanging information between...

Ordovician limestone-marl alternations in the Oslo-Asker District have been interpreted as signaling glacio-eustatic lowstands, which would support a prolonged "Early Palaeozoic Icehouse". However, these rhythmites could alternatively reflect differential diagenesis, without sedimentary trigger. Here, we test both hypotheses through one Darriwilian and three Katian sections. Our methodology con...

The potential for denitrification in marl and peat sediments in the Shark River Slough in the Everglades National Park was determined by the acetylene blockage assay. The influence of nitrate concentration on denitrification rate and N(2)O yield from added nitrate was examined. The effects of added glucose and phosphate and of temperature on the denitrification potential were determined. The se...

Multi-agent systems can be used to address problems in a variety of domains, including robotics, distributed control, telecommunications, and economics. The complexity of many tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must instead discover a solution on their own, using learning. A significant part of the research on multi-agent ...

Multi-agent reinforcement learning (MARL) poses the same learning problem as traditional reinforcement leaning (RL): How can an agent learn to maximize their rewards through interaction with their environment? Traditional RL has formalized this problem by modeling the environment as a Markov decision process (MDP) where the outcome of our agent’s actions are fully explained by the state the wor...

Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting the basic gradient ascent approach with policy prediction. We prove that this augmentation results in a stronger notion of convergence than the basic gradient ascent, that is, strategies converge to a Nash equilibrium wi...