paper-with-me

Papers

TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments

2020-09-10 · Tom Bewley, Jonathan Lawry

In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance. Modern agent architectures, such as those trained by deep reinforcement learning, are currently so lacking in interpretable structure as to effectively be black boxes, but insights may still be gained from an external, behaviourist perspective. Inspired by conceptual spaces theory, we suggest that a versatile first step towards general understanding is to discretise the state space into convex regions, jointly capturing similarities over the agent's action, value function and temporal dynamics within a dataset of observations. We create such a representation using a novel variant of the CART decision tree algorithm, and demonstrate how it facilitates practical understanding of black box agents through prediction, visualisation and rule-based explanation.

📄 PDF Abstract BibTeX arXiv:2009.04743

Code (1)

tombewley/TripleTree 공식 구현

Tasks

Deep Reinforcement LearningExplainable artificial intelligencereinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Modelling Agent Policies with Interpretable Imitation Learning

2020-06-19 · Tom Bewley, Jonathan Lawry, Arthur Richards

As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations. We outline an approach to imitation learning for reverse-engin…

Imitation Learning

Asking the Right Questions: Learning Interpretable Action Models Through Query Answering

2019-12-29 · Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a min…

Am I Building a White Box Agent or Interpreting a Black Box Agent?

2020-07-02 · Tom Bewley

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 t…

Explainable artificial intelligence

Towards Governing Agent's Efficacy: Action-Conditional $β$-VAE for Deep Transparent Reinforcement Learning

2018-11-11 · John Yang, Gyujeong Lee, Minsung Hyun, Simyung Chang 외

We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable way. Such learning approach is risky when…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making

2026-04-08 · Zhaowen Fan, Rongchao Zhang, Yunxiang Han arxiv

Autonomous agents operating in dynamic environments increasingly demand decision-making systems that are both efficient and interpretable. Hence we propose the Event-Retrieve-Action (ERA) framework, an alternative formul…