Related papers: ACTER: Diverse and Actionable Counterfactual Seque…
Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer…
Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i.e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- is essential for…
The prevalence of machine learning models in various industries has led to growing demands for model interpretability and for the ability to provide meaningful recourse to users. For example, patients hoping to improve their diagnoses or…
This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…
Accounting for the fact that users have different sequential patterns, the main drawback of state-of-the-art recommendation strategies is that a fixed sequence length of user-item interactions is required as input to train the models. This…
Counterfactual explanations provide human-understandable reasoning for AI-made decisions by describing minimal changes to input features that would alter a model's prediction. To be truly useful in practice, such explanations must be…
Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation.…
Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods. It allows optimizing a joint action-value function through the maximization of factorized per-agent…
Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been…
Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in…
Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attributes (e.g., brightness, texture) and object categories. Existing test-time adaptation (TTA)…
Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and…
Explainable AI (XAI) systems have been proposed to help people understand how AI systems produce outputs and behaviors. Explainable Reinforcement Learning (XRL) has an added complexity due to the temporal nature of sequential…
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…
Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…
Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…
We present counterfactual planning as a design approach for creating a range of safety mechanisms that can be applied in hypothetical future AI systems which have Artificial General Intelligence. The key step in counterfactual planning is…
Deploying reinforcement learning agents in the real world can be challenging due to the risks associated with learning through trial and error. We propose a task-agnostic method that leverages small sets of safe and unsafe demonstrations to…
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…
Adversarial Imitation Learning (AIL) is a class of popular state-of-the-art Imitation Learning algorithms commonly used in robotics. In AIL, an artificial adversary's misclassification is used as a reward signal that is optimized by any…