Related papers: Relaxing Behavioural Inheritance
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be…
In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value…
Haskell provides type-class-bounded and parametric polymorphism as opposed to subtype polymorphism of object-oriented languages such as Java and OCaml. It is a contentious question whether Haskell 98 without extensions, or with common…
People exhibit a tendency to generalize a novel noun to the basic-level in a hierarchical taxonomy -- a cognitively salient category such as "dog" -- with the degree of generalization depending on the number and type of exemplars. Recently,…
Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…
We propose inheritance and refinement relations for a CSP-based component model (BRIC), which supports a constructive design based on composition rules that preserve classical concurrency properties such as deadlock freedom. The proposed…
Manual modeling in Constraint Programming is a substantial bottleneck, which Constraint Acquisition (CA) aims to automate. However, passive CA methods are prone to over-fitting, often learning models that include spurious global constraints…
This paper develops a refined version of TAPO-description logic for the analysis of information behavior. The framework is treated not as a single homogeneous object logic, but as a layered formalism consisting of a static descriptive layer…
The quality of high-level AI of non-player characters (NPCs) in commercial open-world games (OWGs) has been increasing during the past years. However, due to constraints specific to the game industry, this increase has been slow and it has…
While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between attention mechanisms and multinomial regression. Specifically,…
In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…
In recent work we have presented a novel algorithm for mesh refinement which utilizes a reduced model. In particular, the reduced model is used to monitor the transfer of activity (e.g. mass, energy) from larger to smaller scales. When the…
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…
Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…
We investigate refinement in the context of choreographies. We introduce refinable global choreographies allowing for the underspecification of protocols, whose interactions can be refined into actual protocols. Arbitrary refinements may…
Animals such as rabbits and birds can instantly generate locomotion behavior in reaction to a dynamic, approaching object, such as a person or a rock, despite having possibly never seen the object before and having limited perception of the…