Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Type de record:
paperposter
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Poster presented at the Deep Learning Indaba 2023 by Ulrich Armel Mbou Sob
Similaires
Mava: Fast Parallel Multi-agent Reinforcement Learning in JAXMulti-agent Deep-reinforcement learning (MADRL) based Task offloading in Fog Computing EnvironmentsMachine Learning for Personalized Education: Optimizing Learning Outcomes among Diverse Online Learner Populations in Ghana Using Reinforcement LearningAgentic AI for Ethical Cybersecurity in Uganda: A Reinforcement Learning Framework for Threat Detection in Resource-Constrained EnvironmentsAgentic Artificial Intelligence for Ethical Cybersecurity in Uganda: A Reinforcement Learning Framework for Threat Detection in Resource-Constrained EnvironmentsScalable processing of aggregate functions for data streams in resource-constrained environments