Related papers: Neural Interactive Proofs
Today we have a good theoretical understanding of the representational power of Graph Neural Networks (GNNs). For example, their limitations have been characterized in relation to a hierarchy of Weisfeiler-Lehman (WL) isomorphism tests.…
In multi-prover interactive proofs (MIPs), the verifier is usually non-adaptive. This stems from an implicit problem which we call ``contamination'' by the verifier. We make explicit the verifier contamination problem, and identify a…
We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected…
ProofPeer strives to be a system for cloud-based interactive theorem proving. After illustrating why such a system is needed, the paper presents some of the design challenges that ProofPeer needs to meet to succeed. Contexts are presented…
Interactive behavior modeling of multiple agents is an essential challenge in simulation, especially in scenarios when agents need to avoid collisions and cooperate at the same time. Humans can interact with others without explicit…
Formally verifying the correctness of mathematical proofs is more accessible than ever, however, the learning curve remains steep for many of the state-of-the-art interactive theorem provers (ITP). Deriving the most appropriate subsequent…
We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other…
In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. This area of application has implied new software quality assessment challenges that traditional validation and…
Learning-based methods could provide solutions to many of the long-standing challenges in control. However, the neural networks (NNs) commonly used in modern learning approaches present substantial challenges for analyzing the resulting…
We consider the setting of stochastic multiagent systems modelled as stochastic multiplayer games and formulate an automated verification framework for quantifying and reasoning about agents' trust. To capture human trust, we work with a…
Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical…
We introduce pseudo-deterministic interactive proofs (psdAM): interactive proof systems for search problems where the verifier is guaranteed with high probability to output the same output on different executions. As in the case with…
The notion that cooperation can aid a group of agents to solve problems more efficiently than if those agents worked in isolation is prevalent, despite the little quantitative groundwork to support it. Here we consider a primordial form of…
This work studies the problem of ad hoc teamwork in teams composed of agents with differing computational capabilities. We consider cooperative multi-player games in which each agent's policy is constrained by a private capability…
Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-person actors in partially-observable worlds. To achieve…
Automatic verification deals with the validation by means of computers of correctness certificates. The related tools, usually called proof assistants or interactive provers, provide an interactive environment for the creation of formal…
In multi-prover interactive proofs, the verifier interrogates the provers and attempts to steal their knowledge. Other than that, the verifier's role has not been studied. We have discovered that the verifier plays a much more important…
Albrecht and Stone (2018) state that modeling of changing behaviors remains an open problem "due to the essentially unconstrained nature of what other agents may do". In this work we evaluate the adaptability of neural artificial agents…
High-dimensional policies, such as those represented by neural networks, cannot be reasonably interpreted by humans. This lack of interpretability reduces the trust users have in policy behavior, limiting their use to low-impact tasks such…
Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We…