Explainability in Deep Reinforcement Learning

Heuillet, Alexandre; Couthouis, Fabien; Díaz-Rodríguez, Natalia

doi:10.48550/arxiv.2008.06693

Cited by 3 publications

(4 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a solution to this problem, the explainable AI (XAI) concept was introduced (Gunning and Aha, 2019). XAI systems are implementing different types of explainability ranging, depending on the target audience and their goals and domains (Heuillet, Couthouis, and Díaz-Rodríguez, 2020). The methods include but are not limited to graphs, text commentaries to actions and summation, generated visuals, or augmented vision inputs such as saliency maps and others.…”

Section: The Black Box Problemmentioning

confidence: 99%

Spatial Agent-based Architecture Design Simulation Systems

Kotov¹,

Starke²,

Vukorep³

2022

eCAADe Proceedings

View full text Add to dashboard Cite

This paper presents case studies and analysis of agent-based reinforcement learning (RL) systems towards practical applications for specific architecture/engineering tasks using Unity 3D-based simulation methods. Finding and implementing sufficient abstraction for architecture and engineering problems to be solved by agent-based systems requires broad architectural knowledge and the ability to break down complex problems. Modern artificial intelligence (AI) and machine learning (ML) systems based on artificial neural networks can solve complex problems in different domains such as computer vision, language processing, and predictive maintenance. The paper will give a theoretical overview, such as more theoretical abstractions like zero-sum games, and a comparison of presented games. The application section describes a possible categorization of practical usages. From more general applications to more narrowed ones, we explore current possibilities of RL application in the field of relatable problems. We use the Unity 3D engine as the basis of a robust simulation environment.

show abstract

Section: The Black Box Problemmentioning

confidence: 99%

Spatial Agent-based Architecture Design Simulation Systems

Kotov¹,

Starke²,

Vukorep³

2022

eCAADe Proceedings

View full text Add to dashboard Cite

show abstract

“…Designing more understandable approaches for a broader audience is also a pressing issue to overcome in XRL. We refer the reader to [62], [63], and the references therein for a detailed overview of explainability methods in RL.…”

Section: C) On Explainable Rl (Xrl)mentioning

confidence: 99%

Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial

Feriani¹,

Hossain²

2020

Preprint

View full text Add to dashboard Cite

Deep Reinforcement Learning (DRL) has recently witnessed significant advances that have led to multiple successes in solving sequential decision-making problems in various domains, particularly in wireless communications. The future sixth-generation (6G) networks are expected to provide scalable, low-latency, ultra-reliable services empowered by the application of data-driven Artificial Intelligence (AI). The key enabling technologies of future 6G networks, such as intelligent metasurfaces, aerial networks, and AI at the edge, involve more than one agent which motivates the importance of multi-agent learning techniques. Furthermore, cooperation is central to establishing self-organizing, self-sustaining, and decentralized networks. In this context, this tutorial focuses on the role of DRL with an emphasis on deep Multi-Agent Reinforcement Learning (MARL) for AI-enabled 6G networks. The first part of this paper will present a clear overview of the mathematical frameworks for single-agent RL and MARL. The main idea of this work is to motivate the application of RL beyond the model-free perspective which was extensively adopted in recent years. Thus, we provide a selective description of RL algorithms such as Model-Based RL (MBRL) and cooperative MARL and we highlight their potential applications in 6G wireless networks. Finally, we overview the state-of-the-art of MARL in fields such as Mobile Edge Computing (MEC), Unmanned Aerial Vehicles (UAV) networks, and cell-free massive MIMO, and identify promising future research directions. We expect this tutorial to stimulate more research endeavors to build scalable and decentralized systems based on MARL.

show abstract

“…Considering explanation in an RL context allows extra focus on the types of explanations possible in RL and how they can be combined to provide levels of explanation to better facilitate understanding and acceptance by different users. Heuillet et al [105] and Wallkötter et al [236] have both provided in-depth surveys of the issues and abilities that reinforcement learning and embodied agents can provide. These papers pull together a number of papers that have explored the potential of explainable systems in interactive temporal agents.…”

Section: Introductionmentioning

confidence: 99%

“…Due to this alignment of perception and traditional IML there has been limited research specifically on perception in the context of XRL [105,179]. However, there are two primary issues that make perception in XRL distinct from traditional IML.…”

Section: Introspective Xrl-perceptionmentioning

confidence: 99%

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Dazeley¹,

Vamplew²,

Cruz³

2021

Preprint

View full text Add to dashboard Cite

Broad Explainable Artificial Intelligence (Broad-XAI) moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent's behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms all operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) is relatively recent field of research that aims to develop techniques to extract concepts from the agent's: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce a conceptual framework, called the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. Additionally, we recognise that RL methods have the ability to incorporate a range of technologies to allow agents to adapt to their environment. CXF is designed for the incorporation of many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes and justify its decisions. This paper aims to: establish XRL as a distinct branch of Explainable Artificial Intelligence (XAI); introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper will discuss how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI.

show abstract

Explainability in Deep Reinforcement Learning

Cited by 3 publications

References 84 publications

Spatial Agent-based Architecture Design Simulation Systems

Spatial Agent-based Architecture Design Simulation Systems

Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Contact Info

Product

Resources

About