DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning

2019-09-06 · Theo Jaunet, Romain Vuillemot, Christian Wolf

We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of large temporal vectors updated when the agent moves in an environment and is not trivial to understand due to the number of dimensions, dependencies to past vectors, spatial/temporal correlations, and co-correlation between dimensions. It is often referred to as a black box as only inputs (images) and outputs (actions) are intelligible for humans. Using DRLViz, experts are assisted to interpret decisions using memory reduction interactions, and to investigate the role of parts of the memory when errors have been made (e.g. wrong direction). We report on DRLViz applied in the context of video games simulators (ViZDoom) for a navigation scenario with item gathering tasks. We also report on experts evaluation using DRLViz, and applicability of DRLViz to other scenarios and navigation problems beyond simulation games, as well as its contribution to black box models interpretability and explainability in the field of visual analytics.

📄 PDF Abstract BibTeX arXiv:1909.02982

Code (1)

sical/drlviz 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Generating Explanations from Deep Reinforcement Learning Using Episodic Memory

2022-05-18 · Sam Blakeman, Denis Mareschal

Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario

2020-06-24 · Francisco Cruz, Richard Dazeley, Peter Vamplew, Ithan Moreira

Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To in…

Action Understanding Decision Making reinforcement-learning Reinforcement Learning+1

An Efficient Streaming Video Understanding Framework with Agentic Control

2026-05-18 · Jinming Liu, Jianguo Huang, Zhaoyang Jia, Jiahao Li 외 arxiv

Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compression or reliance on a single model, forcin…

Reinforcement Learning

ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization

2026-03-18 · Panuganti Chirag Sai, Gandholi Sarat, R. Raghunatha Sarma, Venkata Kalyan Tavva 외 arxiv

Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy an…

Reinforcement Learning

On Memory Mechanism in Multi-Agent Reinforcement Learning

2019-09-11 · Yilun Zhou, Derrik E. Asher, Nicholas R. Waytowich, Julie A. Shah

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solvi…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)