Rohan Paleja
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent games.
The paper proposes D-BOS, a novel differentiable method that shapes opponent behavior by directly manipulating the opponent's inferred belief state, outperforming existing techniques in multi-agent games.
This paper extends Heterogeneous Policy Networks (HetNet) to support scaling heterogeneous robot teams and enables end-to-end training for learning highly efficient binarized messaging.
Papers
Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination
Esmaeil Seraj, Rohan Paleja, Luis Pimentel, Kin Man Lee +6 more
This paper extends Heterogeneous Policy Networks (HetNet) to support scaling heterogeneous robot teams and enables end-to-end training for learning highly efficient binarized messaging.