Anticipatory thinking drives our ability to manage risk - identification and mitigation - in everyday life, from bringing an umbrella when it might rain to buying car insurance. As AI systems become part of everyday life, they too have begun to manage risk. Autonomous vehicles log millions of miles, StarCraft and Go agents have similar capabilities to humans, implicitly managing risks presented by their opponents. To further increase performance in these tasks, out-of-distribution evaluation can characterize a model's bias, what we view as a type of risk management. However, learning to identify and mitigate low-frequency, high-impact risks is at odds with the observational bias required to train machine learning models. StarCraft and Go are closed-world domains whose risks are known and mitigations well documented, ideal for learning through repetition. Adversarial filtering datasets provide difficult examples but are laborious to curate and static, both barriers to real-world risk management. Adversarial robustness focuses on model poisoning under the assumption there is an adversary with malicious intent, without considering naturally occurring adversarial examples. These methods are all important steps towards improving risk management but do so without considering open-worlds. We unify these open-world risk management challenges with two contributions. The first is our perception challenges, designed for agents with imperfect perceptions of their environment whose consequences have a high impact. Our second contribution are cognition challenges, designed for agents that must dynamically adjust their risk exposure as they identify new risks and learn new mitigations. Our goal with these challenges is to spur research into solutions that assess and improve the anticipatory thinking required by AI agents to manage risk in open-worlds and ultimately the real-world.

Developing artificial intelligence approaches to overcome novel, unexpected circumstances is a difficult, unsolved problem. One challenge to advancing the state of the art in novelty accommodation is the availability of testing frameworks for evaluating performance against novel situations. Recent novelty generation approaches in domains such as Science Birds and Monopoly leverage human domain expertise during the search to discover new novelties. Such approaches introduce human guidance before novelty generation occurs and yield novelties that can be directly loaded into a simulated environment. We introduce a new approach to novelty generation that uses abstract models of environments (including simulation domains) that do not require domain-dependent human guidance to generate novelties. A key result is a larger, often infinite space of novelties capable of being generated, with the trade-off being a requirement to involve human guidance to select and filter novelties post generation. We describe our Human-in-the-Loop novelty generation process using our open-source novelty generation library to test baseline agents in two domains: Monopoly and VizDoom. Our results shows the Human-in-the-Loop method enables users to develop, implement, test, and revise novelties within 4 hours for both Monopoly and VizDoom domains.

To be robust to surprising developments, an intelligent agent must be able to respond to many different types of unexpected change in the world. To date, there are no general frameworks for defining and characterizing the types of environment changes that are possible. We introduce a formal and theoretical framework for defining and categorizing environment transformations, changes to the world an agent inhabits. We introduce two types of environment transformation: R-transformations which modify environment dynamics and T-transformations which modify the generation process that produces scenarios. We present a new language for describing domains, scenario generators, and transformations, called the Transformation and Simulator Abstraction Language (T-SAL), and a logical formalism that rigorously defines these concepts. Then, we offer the first formal and computational set of tests for eight categories of environment transformations. This domain-independent framework paves the way for describing unambiguous classes of novelty, constrained and domain-independent random generation of environment transformations, replication of environment transformation studies, and fair evaluation of agent robustness.

Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial intelligence. The key characteristic is to declaratively represent and then monitor traces of cognitive activity in an intelligent system in order to manage the performance of cognition itself. Improvements in cognition then lead to improvements in behavior and thus performance. We illustrate these concepts with an agent implementation in a cognitive architecture called MIDCA and show the value of metacognition in problem-solving. The results illustrate how computational metacognition improves performance by changing cognition through meta-level goal operations and learning.

Anticipatory thinking is a complex cognitive process for assessing and managing risk in many contexts. Humans use anticipatory thinking to identify potential future issues and proactively take actions to manage their risks. In this paper we define a cognitive systems approach to anticipatory thinking as a metacognitive goal reasoning mechanism. The contributions of this paper include (1) defining anticipatory thinking in the MIDCA cognitive architecture, (2) operationalizing anticipatory thinking as a three step process for managing risk in plans, and (3) a numeric risk assessment calculating an expected cost-benefit ratio for modifying a plan with anticipatory actions.

Dungeon Crawl Stone Soup is a popular, single-player, free and open-source rogue-like video game with a sufficiently complex decision space that makes it an ideal testbed for research in cognitive systems and, more generally, artificial intelligence. This paper describes the properties of Dungeon Crawl Stone Soup that are conducive to evaluating new approaches of AI systems. We also highlight an ongoing effort to build an API for AI researchers in the spirit of recent game APIs such as MALMO, ELF, and the Starcraft II API. Dungeon Crawl Stone Soup's complexity offers significant opportunities for evaluating AI and cognitive systems, including human user studies. In this paper we provide (1) a description of the state space of Dungeon Crawl Stone Soup, (2) a description of the components for our API, and (3) the potential benefits of evaluating AI agents in the Dungeon Crawl Stone Soup video game.

Non-player characters (NPCs) in video games are a common form of frustration for players because they generally provide no explanations for their actions or provide simplistic explanations using fixed scripts. Motivated by this, we consider a new design for agents that can learn about their environments, accomplish a range of goals, and explain what they are doing to a supervisor. We propose a framework for studying this type of agent, and compare it to existing reinforcement learning and self-motivated agent frameworks. We propose a novel design for an initial agent that acts within this framework. Finally, we describe an evaluation centered around the supervisor's satisfaction and understanding of the agent's behavior.

Human-agent teaming is a difficult yet relevant problem domain to which many goal reasoning systems are well suited, due to their ability to accept outside direction and (relatively) human-understandable internal state. We propose a formal model, and multiple variations on a multi-agent problem, to clarify and unify research in goal reasoning. We describe examples of these concepts, and propose standard evaluation methods for goal reasoning agents that act as a member of a team or on behalf of a supervisor.

Cognitive agents operating in complex and dynamic domains benefit from significant goal management. Operations on goals include formulation, selection, change, monitoring and delegation in addition to goal achievement. Here we model these operations as transformations on goals. An agent may observe events that affect the agent’s ability to achieve its goals. Hence goal transformations allow unachievable goals to be converted into similar achievable goals. This paper examines an implementation of goal change within a cognitive architecture. We introduce goal transformation at the metacognitive level as well as goal transformation in an automated planner and discuss the costs and benefits of each approach. We evaluate goal change in the MIDCA architecture using a resource-restricted planning domain, demonstrating a performance benefit due to goal operations.

The results of autonomy are often some mechanism Research on cognitive architectures have made significant by which we automate system behavior and decision-making contributions over the years including the ability to reason computationally. We claim that for a system to exhibit with multiple knowledge modes (Laird 2012), to introspectively self-regulated autonomy, however, it must have a model of examine the rationale for a decision (Forbus, Klenk itself in addition to the usual model of the world. Like selfregulated and Hinrichs 2009), and the ability to learn knowledge of learning (e.g., Bjork, Dunlosky and Kornell 2013), varied levels of abstraction (Langley and Choi 2006). Comparatively whereby a learner manages the pace, resources, and goals of less research efforts examine the metacognitive learning, self-regulated autonomy involves a system that contributions to effective decision-making and behavior.