Loading patent…
AssigneeMassachusetts Institute of Technology
InventorsDhaval Adjodah, Alex Paul Pentland, Esteban Moro, Yan Leng, Peter Krafft, Daniel Calacci, Abhimanyu Dubey
Estimating the term…
In some implementations of this invention, the performance of a network of reinforcement learning agents is maximized by optimizing the communication topology between the agents for the communication of gradients, weights or rewards. For instance, a sparse Erdos-Renyi network may be employed, and network density may be selected in such a way as to maximize reachability and to minimize homogeneity. In some cases, a sparse network topology is employed for massively distributed learning, such as across entire fleets of autonomous vehicles or mobile phones that learn from each other instead of requiring a master to coordinate learning.
A method comprising maximizing performance of a network of reinforcement learning agents by optimizing communication topology between the agents for communication of gradients, weights or rewards.
A method comprising improving performance of a network of reinforcement learning agents by improving communication topology between the agents for communication of gradients, weights or rewards.
A method comprising performing a reinforcement learning algorithm on a network wherein:
Dependencies are inferred from the claim text.