Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality. (arXiv:2205.13521v1 [cs.AI])

Finding different solutions to the same problem is a key aspect of
intelligence associated with creativity and adaptation to novel situations. In
reinforcement learning, a set of diverse policies can be useful for
exploration, transfer, hierarchy, and robustness. We propose DOMiNO, a method
for Diversity Optimization Maintaining Near Optimality. We formalize the
problem as a Constrained Markov Decision Process where the objective is to find
diverse policies, measured by the distance between the state occupancies of the
policies in the …

ai arxiv diversity domino near optimization