Wargames have a long history in the development of military strategy and the response of nations to threats or attacks. The advent of artificial intelligence (AI) promises better decision-making and increased military effectiveness. However, there is still debate about how AI systems, especially large language models (LLMs), behave as compared to humans. To this end, we use a wargame experiment with 107 national security expert human players designed to look at crisis escalation in a fictional US-China scenario and compare human players to LLM-simulated responses. We find considerable agreement in the LLM and human responses but also significant quantitative and qualitative differences between simulated and human players in the wargame, motivating caution to policymakers before handing over autonomy or following AI-based strategy recommendations.
Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty. Unfortunately, online CPOMDP planning is extremely difficult in large or continuous problem domains. In many large robotic domains, hierarchical decomposition can simplify planning by using tools for low-level control given high-level action primitives (options). We introduce Constrained Options Belief Tree Search (COBeTS) to leverage this hierarchy and scale online search-based CPOMDP planning to large robotic problems. We show that if primitive option controllers are defined to satisfy assigned constraint budgets, then COBeTS will satisfy constraints anytime. Otherwise, COBeTS will guide the search towards a safe sequence of option primitives, and hierarchical monitoring can be used to achieve runtime safety. We demonstrate COBeTS in several safety-critical, constrained partially observable robotic domains, showing that it can plan successfully in continuous CPOMDPs while non-hierarchical baselines cannot.
While transformers have pioneered attention-driven architectures as a cornerstone of research, their dependence on explicitly contextual information underscores limitations in their abilities to tacitly learn overarching textual themes. This study investigates social media data as a source of distributed patterns, challenging the heuristic paradigm of performance benchmarking. In stark contrast to networks that rely on capturing complex long-term dependencies, models of online data inherently lack structure and are forced to learn underlying patterns in the aggregate. To properly represent these abstract relationships, this research dissects empirical social media corpora into their elemental components and analyzes over two billion tweets across population-dense locations. Exploring the relationship between location and vernacular in Twitter data, we employ Bag-of-Words models specific to each city and evaluate their respective representation. This demonstrates that hidden insights can be uncovered without the crutch of advanced algorithms and demonstrates that even amidst noisy data, geographic location has a considerable influence on online communication. This evidence presents tangible insights regarding geospatial communication patterns and their implications in social science. It also challenges the notion that intricate models are prerequisites for pattern recognition in natural language, aligning with the evolving landscape that questions the embrace of absolute interpretability over abstract understanding. This study bridges the divide between sophisticated frameworks and intangible relationships, paving the way for systems that blend structured models with conjectural reasoning.
As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged. Despite notable progress, the performance of these systems can significantly diminish due to adversarial attacks or environmental changes, leading to overconfident predictions, failures to detect input faults, and an inability to generalize in unexpected scenarios. This paper proposes a holistic assessment methodology for the reliability of ML systems. Our framework evaluates five key properties: in-distribution accuracy, distribution-shift robustness, adversarial robustness, calibration, and out-of-distribution detection. A reliability score is also introduced and used to assess the overall system reliability. To provide insights into the performance of different algorithmic approaches, we identify and categorize state-of-the-art techniques, then evaluate a selection on real-world tasks using our proposed reliability metrics and reliability score. Our analysis of over 500 models reveals that designing for one metric does not necessarily constrain others but certain algorithmic techniques can improve reliability across multiple metrics simultaneously. This study contributes to a more comprehensive understanding of ML reliability and provides a roadmap for future research and development.
In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022. We identify key open research questions in resource allocation, planning, and interventions for biodiversity conservation, highlighting conservation challenges that not only require AI solutions, but also require novel methodological advances. In addition to providing a summary of the workshop talks and discussions, we hope this document serves as a call-to-action to orient the expansion of algorithmic decision-making approaches to prioritize real-world conservation challenges, through collaborative efforts of ecologists, conservation decision-makers, and AI researchers.
Real-world planning problems$\unicode{x2014}$including autonomous driving and sustainable energy applications like carbon storage and resource exploration$\unicode{x2014}$have recently been modeled as partially observable Markov decision processes (POMDPs) and solved using approximate methods. To solve high-dimensional POMDPs in practice, state-of-the-art methods use online planning with problem-specific heuristics to reduce planning horizons and make the problems tractable. Algorithms that learn approximations to replace heuristics have recently found success in large-scale problems in the fully observable domain. The key insight is the combination of online Monte Carlo tree search with offline neural network approximations of the optimal policy and value function. In this work, we bring this insight to partially observed domains and propose BetaZero, a belief-state planning algorithm for POMDPs. BetaZero learns offline approximations based on accurate belief models to enable online decision making in long-horizon problems. We address several challenges inherent in large-scale partially observable domains; namely challenges of transitioning in stochastic environments, prioritizing action branching with limited search budget, and representing beliefs as input to the network. We apply BetaZero to various well-established benchmark POMDPs found in the literature. As a real-world case study, we test BetaZero on the high-dimensional geological problem of critical mineral exploration. Experiments show that BetaZero outperforms state-of-the-art POMDP solvers on a variety of tasks.
Estimating the distribution over failures is a key step in validating autonomous systems. Existing approaches focus on finding failures for a small range of initial conditions or make restrictive assumptions about the properties of the system under test. We frame estimating the distribution over failure trajectories for sequential systems as Bayesian inference. Our model-based approach represents the distribution over failure trajectories using rollouts of system dynamics and computes trajectory gradients using automatic differentiation. Our approach is demonstrated in an inverted pendulum control system, an autonomous vehicle driving scenario, and a partially observable lunar lander. Sampling is performed using an off-the-shelf implementation of Hamiltonian Monte Carlo with multiple chains to capture multimodality and gradient smoothing for safe trajectories. In all experiments, we observed improvements in sample efficiency and parameter space coverage compared to black-box baseline approaches. This work is open sourced.
Rather than augmenting rewards with penalties for undesired behavior, Constrained Partially Observable Markov Decision Processes (CPOMDPs) plan safely by imposing inviolable hard constraint value budgets. Previous work performing online planning for CPOMDPs has only been applied to discrete action and observation spaces. In this work, we propose algorithms for online CPOMDP planning for continuous state, action, and observation spaces by combining dual ascent with progressive widening. We empirically compare the effectiveness of our proposed algorithms on continuous CPOMDPs that model both toy and real-world safety-critical problems. Additionally, we compare against the use of online solvers for continuous unconstrained POMDPs that scalarize cost constraints into rewards, and investigate the effect of optimistic cost propagation.
An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo sampling is inefficient. Adaptive importance sampling approaches have been developed for rare event estimation but do not scale well to sequential systems with long horizons. In this work, we develop two adaptive importance sampling algorithms that can efficiently estimate the probability of rare events for sequential decision making systems. The basis for these algorithms is the minimization of the Kullback-Leibler divergence between a state-dependent proposal distribution and a target distribution over trajectories, but the resulting algorithms resemble policy gradient and value-based reinforcement learning. We apply multiple importance sampling to reduce the variance of our estimate and to address the issue of multi-modality in the optimal proposal distribution. We demonstrate our approach on a control task with both continuous and discrete actions spaces and show accuracy improvements over several baselines.