Search Results for author:
Found 12 papers, 3 papers with code
Sequential Harmful Shift Detection Without Labels
We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels.
Interpreting Language Reward Models via Contrastive Explanations
We see our method as a flexible framework for RM explanation, providing a basis for more interpretable and trustworthy LLM alignment.
Counterfactual Metarules for Local and Global Recourse
We introduce T-CREx, a novel model-agnostic method for local and global counterfactual explanation (CE), which summarises recourse options for both individuals and groups in the form of human-readable rules.
Zero-Shot Reinforcement Learning from Low Quality Data
Zero-shot reinforcement learning (RL) promises to provide agents that can perform any task in an environment after an offline, reward-free pre-training phase.
Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback
We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback.
Reward Learning with Trees: Methods and Evaluation
Recent efforts to learn reward functions from human feedback have tended to use deep neural networks, whose lack of transparency hampers our ability to explain agent behaviour or verify alignment.
Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning
We generalise the problem of reward modelling (RM) for reinforcement learning (RL) to handle non-Markovian rewards.
Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction
We introduce a data-driven, model-agnostic technique for generating a human-interpretable summary of the salient points of contrast within an evolving dynamical system, such as the learning process of a control agent.
Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem.
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments
In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance.
Deep Reinforcement Learning
Explainable artificial intelligence
+2
Am I Building a White Box Agent or Interpreting a Black Box Agent?
The rule extraction literature contains the notion of a fidelity-accuracy dilemma: when building an interpretable model of a black box function, optimising for fidelity is likely to reduce performance on the underlying task, and vice versa.
Modelling Agent Policies with Interpretable Imitation Learning
As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations.
