Related papers: Self-Explaining Deviations for Coordination
Adjustable autonomy refers to entities dynamically varying their own autonomy, transferring decision-making control to other entities (typically agents transferring control to human users) in key situations. Determining whether and when…
Counterfactual Explanations (CEs) are a powerful technique used to explain Machine Learning models by showing how the input to a model should be minimally changed for the model to produce a different output. Similar proposals have been made…
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…
To be helpful assistants, AI agents must be aware of their own capabilities and limitations. This includes knowing when to answer from parametric knowledge versus using tools, when to trust tool outputs, and when to abstain or hedge. Such…
Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g.,…
In two-player cooperative games, agents can play together effectively when they have accurate assumptions about how their teammate will behave, but may perform poorly when these assumptions are inaccurate. In language games, failure may be…
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…
Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to…
We reproduce apparently complex cellular automaton behaviour with simple partial differential equations as developed in (Keane 09). Our PDE model easily explains behaviour observed in selected scenarios of the cellular automaton wargame…
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation…
Reinforcement learning algorithms can train agents that solve problems in complex, interesting environments. Normally, the complexity of the trained agent is closely related to the complexity of the environment. This suggests that a highly…
Natural language has the universal properties of being compositional and grounded in reality. The emergence of linguistic properties is often investigated through simulations of emergent communication in referential games. However, these…
Deep learning-based methods have achieved a breakthrough in image anomaly detection, but their complexity introduces a considerable challenge to understanding why an instance is predicted to be anomalous. We introduce a novel explanation…
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions…
In many joint-action scenarios, humans and robots have to coordinate their movements to accomplish a given shared task. Lifting an object together, sawing a wood log, transferring objects from a point to another are all examples where motor…
Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for some reward…
An evolving population, in which individual members (`agents') adapt their behaviour according to past experience, is of central importance to many disciplines. Because of their limited knowledge and capabilities, agents are forced to make…
Recent advances in Large Language Models (LLMs) have upgraded them from sophisticated text generators to autonomous agents capable of cooperation and tool use in multi-agent systems (MAS). However, it remains unclear how disagreements shape…
When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act…
Empirical evidence shows that human behaviour often deviates from game-theoretical rationality. For instance, humans may hold unrealistic expectations about future outcomes. As the evolutionary roots of such biases remain unclear, we…