Related papers: Reduced Implication-bias Logic Loss for Neuro-Symb…

Inverse reinforcement learning (IRL) aims to infer an agent's preferences (represented as a reward function $R$) from their behaviour (represented as a policy $\pi$). To do this, we need a behavioural model of how $\pi$ relates to $R$. In…

Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs, ls learns to split this dataset so that predictors…

Spurious correlations are everywhere. While humans often do not perceive them, neural networks are notorious for learning unwanted associations, also known as biases, instead of the underlying decision rule. As a result, practitioners are…

Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them difficult to interpret. In contrast, symbolic policies allow…

We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these…

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in the current IRL setting, the learner is isolated from the expert and can only passively…

Understanding an agent's goals from its behavior is fundamental to aligning AI systems with human intentions. Existing goal recognition methods typically rely on an optimal goal-oriented policy representation, which may differ from the…

Pretraining on human corpus and then finetuning in a simulator has become a standard pipeline for training a goal-oriented dialogue agent. Nevertheless, as soon as the agents are finetuned to maximize task completion, they suffer from the…

Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced…

The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the…

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate…

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind…

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and…

Physics-Informed Machine Learning (PIML) has gained momentum in the last 5 years with scientists and researchers aiming to utilize the benefits afforded by advances in machine learning, particularly in deep learning. With large scientific…

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of…

Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation function that translates…

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. To do this, we need a model of how $\pi$ relates to $R$. In the current literature, the most common models are optimality, Boltzmann…

Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we…