Canada

Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent&#39;s selected choice of action. 
In this work, we propose ``COViz&#39;&#39;, a new local explanation method that visually compares the outcome of an agent&#39;s chosen action to a counterfactual one. In contrast to most local explanations that provide state-limited observations of the agent&#39;s motivation, our method depicts alternative trajectories the agent could have taken from the given state and their outcomes. 
We evaluated the usefulness of COViz in supporting people&#39;s understanding of agents&#39; preferences and compare it with reward decomposition, a local explanation method that describes an agent&#39;s expected utility for different actions by decomposing it into meaningful reward types. Furthermore, we examine the complementary benefits of integrating both methods. Our results show that such integration significantly improved participants&#39; performance.

AAAI 2024

Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes | VIDEO

explainable reinforcement learning

counterfactual explanations

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

AAAI 2025

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Explainable reinforcement learning (XRL) methods aim to help elucidate agent policies and decision-making processes. The majority of XRL approaches focus on local explanations, seeking to shed light on the reasons an agent acts the way it does at a specific world state. While such explanations are both useful and necessary, they typically do not portray the outcomes of the agent's selected choice of action. 
In this work, we propose ``COViz'', a new local explanation method that visually compares the outcome of an agent's chosen action to a counterfactual one. In contrast to most local explanations that provide state-limited observations of the agent's motivation, our method depicts alternative trajectories the agent could have taken from the given state and their outcomes. 
We evaluated the usefulness of COViz in supporting people's understanding of agents' preferences and compare it with reward decomposition, a local explanation method that describes an agent's expected utility for different actions by decomposing it into meaningful reward types. Furthermore, we examine the complementary benefits of integrating both methods. Our results show that such integration significantly improved participants' performance.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

This paper introduces the design, development, and deployment of a Virtual Driving Instructor (VDI) for enhanced driver education. 
The VDI provides personalized, real-time feedback to students in a driving simulator, addressing some of the limitations of traditional driver instruction. 
Employing a hybrid AI system, the VDI combines rule-based agents, learning-based agents, knowledge graphs, and Bayesian networks to assess and monitor student performance in a comprehensive manner. 
Implemented in multiple simulators at a driving school in Norway, the system aims to leverage AI and driving simulation to improve both the learning experience and the efficiency of instruction. 
Initial feedback from students has been largely positive, highlighting the effectiveness of this integration while also pointing to areas for further improvement. 
This work marks a significant stride in infusing technology into driver education, offering a scalable and efficient approach to instruction.

The Virtual Driving Instructor: Multi-Agent System Collaborating via Knowledge Graph for Scalable Driver Education

The Neutron star Interior Composition Explorer (NICER) is an International Space Station (ISS)-based Space Telescope developed by NASA and devoted to the study of high-energy X-Ray sources in the universe, including but not limited to neutron stars, pulsars, and black holes in stellar systems and active galactic nuclei (AGN). One prominent problem with NICER observations is the highly variable background spectra, obscuring actual signals of astrophysical sources and negatively affecting scientific analysis of the targets. Therefore, obtaining accurate estimations of the background spectra is crucial to filter the noise and facilitate better scientific discoveries of new astronomical objects. In this paper, we propose the very first Deep Neural Network architecture to model the NICER background spectra variation using information about the spacecraft and telescope associated with each observation. In particular, we develop a BERT-based architecture with tokenizers applied to different groups of features in our tabular dataset. We also introduce an adapted Tabular Deep Residual Network architecture as the predictor following the Transformer modules in our network. We show that our model outperforms the current state-of-the-art background model developed by the NICER team in most evaluation metrics. Finally, we discuss pathways and future work for the deployment of this model on NASA’s next versions of HEASARC Software packages.

BERTground: A Transformer-Based Model of Background Spectra on the ISS-Based NICER Space Telescope

Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants’ data. In addition, each participant would expect to obtain a personalized model tailored for its local data characteristics from the FL in such a scenario. In this work, we propose a new FL framework with federated modality-specific encoders and multimodal anchors (FedMEMA) to simultaneously address the two concurrent issues. Above all, FedMEMA employs an exclusive encoder for each modality to account for the inter-modal heterogeneity in the first place. In the meantime, while the encoders are shared by the participants, the decoders are personalized to meet individual needs. Specifically, a server with full-modal data employs a fusion decoder to aggregate and fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation reversely. Meanwhile, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the encoder parameters. On the other end, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up the information loss due to absent modalities while adapting the representations of present ones. FedMEMA is validated on the BraTS 2020 benchmark for multimodal brain tumor segmentation. Results show that it outperforms various up-to-date methods for multimodal and personalized FL and that its novel designs are effective. Our code is available.

Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation | VIDEO

Many decision and optimization problems have natural extensions as counting problems. The best known example is the Boolean satisfiability problem (SAT), where we want to count the satisfying assignments of truth values to the variables, which is known as the #SAT problem. Likewise, for discrete optimization problems, we want to count the states on which the objective function attains the optimal value. Both SAT and discrete optimization can be formulated as selective marginalize a product function (MPF) queries. Here, we show how general selective MPF queries can be extended for model counting. MPF queries are encoded as tensor hypernetworks over suitable semirings that can be solved by generic tensor hypernetwork contraction algorithms. Our model counting extension is again an MPF query, on an extended semiring, that can be solved by the same contraction algorithms. Model counting is required for uniform model sampling. We show how the counting extension can be further extended for model sampling by constructing yet another semiring. We have implemented the model counting and sampling extensions. Experiments show that our generic approach is competitive with the state of the art in model counting and model sampling.

Model Counting and Sampling via Semiring Extensions | VIDEO

Query answering for Knowledge Bases (KBs) amounts to extracting information from the various models of a KB, and presenting the user with an object that represents such information. In the vast majority of cases, this object consists of those tuples of constants that satisfy the query expression either in every model (certain answers) or in some model (possible answers). However, similarly to the case of incomplete databases, both these forms of answers are a lossy representation of all the knowledge inferable from the query and the queried KB. In this paper, we illustrate a formal framework to characterize the information that query answers for KBs are able to represent. As a first application of the framework, we study the informativeness of current query answering approaches, including the recently introduced partial answers. We then define a novel notion of answers, allowing repetition of variables across answer tuples. We show that these answers are capable of representing a meaningful form of information, and we also study their data complexity properties.

What Does a Query Answer Tell You? Informativeness of Query Answers for Knowledge Bases

This study proposes and evaluates a new Bayesian network classifier (BNC) having an I-map structure with the fewest class variable parameters among all structures for which the class variable has no parent. Moreover, a new learning algorithm to learn our proposed model is presented. The proposed method is guaranteed to obtain the true classification probability asymptotically. Moreover, the method has lower computational costs than those of exact learning BNC using marginal likelihood. Comparison experiments have demonstrated the superior performance of the proposed method.

Learning Bayesian Network Classifiers to Minimize the Class Variable Parameters

While the question of misspecified objectives has gotten much attention in recent years, most works in this area primarily focus on the challenges related to the complexity of the objective specification mechanism (for example, the use of reward functions). However, the complexity of the objective specification mechanism is just one of many reasons why the user may have misspecified their objective. A foundational cause for misspecification that is being overlooked by these works is the inherent asymmetry in human expectations about the agent's behavior and the behavior generated by the agent for the specified objective. To address this, we propose a novel formulation for the objective misspecification problem that builds on the human-aware planning literature, which was originally introduced to support explanation and explicable behavioral generation. Additionally, we propose a first-of-its-kind interactive algorithm that is capable of using information generated under incorrect beliefs about the agent to determine the true underlying goal of the user.

Goal Alignment: Re-analyzing Value Alignment Problems Using Human-Aware AI | VIDEO

Decision making under uncertainty in dynamic environments is a fundamental AI problem in which agents need to determine which decisions (or actions) to make at each time step to maximise their expected utility. Dynamic decision networks (DDNs) are an extension of dynamic Bayesian networks with decisions and utilities. DDNs can be used to compactly represent Markov decision processes (MDPs). We propose a novel algorithm called mapl-cirup that leverages knowledge compilation techniques developed for (dynamic) Bayesian networks to perform inference and gradient-based learning in DDNs. Specifically, we knowledge-compile the Bellman update present in DDNs into dynamic decision circuits and evaluate them within an (algebraic) model counting framework. In contrast to other exact symbolic MDP approaches, we obtain differentiable circuits that enable gradient-based parameter learning.

Inference and Learning in Dynamic Decision Networks Using Knowledge Compilation

This paper addresses the problem of inventing and using hierarchical representations for stochastic robot-planning problems. Rather than using hand-coded state or action representations as input, it presents new methods for learning how to create a high-level action representation for long-horizon, sparse reward robot planning problems in stochastic settings with unknown dynamics. After training, this system yields a robot-specific but environment independent planning system. Given new problem instances in unseen stochastic environments, it first creates zero-shot options (without any experience on the new environment) with dense pseudo-rewards and then uses them to solve the input problem in a hierarchical planning and refinement process. Theoretical results identify sufficient conditions for completeness of the presented approach. Extensive empirical analysis shows that even in settings that go beyond these sufficient conditions, this approach convincingly outperforms baselines by 2x in terms of solution time with orders of magnitude improvement in solution quality.

Hierarchical Planning and Learning for Robots in Stochastic Settings Using Zero-Shot Option Invention

Lifted probabilistic inference exploits symmetries in a probabilistic model to allow for tractable probabilistic inference with respect to domain sizes. To apply lifted inference, a lifted representation has to be obtained, and to do so, the so-called colour passing algorithm is the state of the art. The colour passing algorithm, however, is bound to a specific inference algorithm and we found that it ignores commutativity of factors while constructing a lifted representation. We contribute a modified version of the colour passing algorithm that uses logical variables to construct a lifted representation independent of a specific inference algorithm while at the same time exploiting commutativity of factors during an offline-step. Our proposed algorithm efficiently detects more symmetries than the state of the art and thereby drastically increases compression, yielding significantly faster online query times for probabilistic inference when the resulting model is applied.

Downloads

Next from AAAI 2024

The Virtual Driving Instructor: Multi-Agent System Collaborating via Knowledge Graph for Scalable Driver Education

Similar lecture

Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning