Search Results for author: Prashan Madumal

Found 6 papers, 2 papers with code

Searching k-Optimal Goals for an Orienteering Problem on a Specialized Graph with Budget Constraints

no code implementations2 Nov 2020 Abhinav Sharma, Advait Deshpande, Yanming Wang, Xinyi Xu, Prashan Madumal, Anbin Hou

We propose a novel non-randomized anytime orienteering algorithm for finding k-optimal goals that maximize reward on a specialized graph with budget constraints.

Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors

1 code implementation27 Jun 2020 Ruihan Zhang, Prashan Madumal, Tim Miller, Krista A. Ehinger, Benjamin I. P. Rubinstein

Based on the requirements of fidelity (approximate models to target models) and interpretability (being meaningful to people), we design measurements and evaluate a range of matrix factorization methods with our framework.

Clustering Dimensionality Reduction +1

Distal Explanations for Model-free Explainable Reinforcement Learning

no code implementations28 Jan 2020 Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere

In this paper we introduce and evaluate a distal explanation model for model-free reinforcement learning agents that can generate explanations for `why' and `why not' questions.

reinforcement-learning Reinforcement Learning +1

Explainable Reinforcement Learning Through a Causal Lens

2 code implementations27 May 2019 Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere

In this paper, we use causal models to derive causal explanations of behaviour of reinforcement learning agents.

counterfactual reinforcement-learning +4

A Grounded Interaction Protocol for Explainable Artificial Intelligence

no code implementations5 Mar 2019 Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere

Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Cannot find the paper you are looking for? You can Submit a new open access paper.