1 code implementation • 8 Nov 2020 • Junha Roh, Christoforos Mavrogiannis, Rishabh Madan, Dieter Fox, Siddhartha S. Srinivasa
Our key insight is that the geometric structure of the intersection and the incentive of agents to move efficiently and avoid collisions (rationality) reduces the space of likely behaviors, effectively relaxing the problem of trajectory prediction.
no code implementations • 27 Jun 2019 • Anirban Santara, Rishabh Madan, Balaraman Ravindran, Pabitra Mitra
Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment.