Reinforcement Learning for Constraint Satisfaction Game Agents

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Praveen, Amritesh, Venkat, Gagan
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2026
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901798419169280
author Praveen, Amritesh
Venkat, Gagan
author_facet Praveen, Amritesh
Venkat, Gagan
contents <p>This work explores reinforcement learning for constraint satisfaction game environments, progressing from tabular Q-learning and DQN experiments to an adversarial PPO-based Wumpus agent. The system transforms the traditional static Wumpus into an adaptive RL-driven adversary capable of learning pursuit behaviour through scent-memory tracking and reward shaping. The project includes a full-stack deployment using FastAPI, React, Firebase, and Gymnasium-compatible training environments.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20076630
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Reinforcement Learning for Constraint Satisfaction Game Agents
Praveen, Amritesh
Venkat, Gagan
<p>This work explores reinforcement learning for constraint satisfaction game environments, progressing from tabular Q-learning and DQN experiments to an adversarial PPO-based Wumpus agent. The system transforms the traditional static Wumpus into an adaptive RL-driven adversary capable of learning pursuit behaviour through scent-memory tracking and reward shaping. The project includes a full-stack deployment using FastAPI, React, Firebase, and Gymnasium-compatible training environments.</p>
title Reinforcement Learning for Constraint Satisfaction Game Agents
url https://doi.org/10.5281/zenodo.20076630