Martin Rinard

Abstract: We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.

TL;DR: This work formalizes SPPL in terms of a novel translation strategy from probabilistic programs to a semantic domain of sum-product representations, and presents new algorithms for exactly conditioning on and computing probabilities of queries, and proves their soundness under the semantics.

TL;DR: In this paper , the authors studied the emergence of locally suboptimal behavior in finitely repeated games with complete information and proved sufficient and necessary conditions on the stage game G that ensures that, for all T and all subgame-perfect equilibria of the repeated game G(T), the strategy profile at every round of G (T) forms a Nash equilibrium.

TL;DR: OSUIF is an extension to SUIF 2.0 that provides support for the compilation of object-oriented languages and extends standard SUIF in three main areas: symbol table, intermediate language, and exception handling.

TL;DR: In this paper, a communication system receives a binary sequence from a sensor, identifies a power consuming characteristic of the binary sequence, and determines an error component configured to reduce the power consuming characteristics of binary sequence.