JaxMARL: Multi-Agent RL Environments in JAX.
Alexander RutherfordBenjamin EllisMatteo GalliciJonathan CookAndrei LupuGarðar IngvarssonTimon WilliAkbir KhanChristian Schröder de WittAlexandra SoulySaptarashmi BandyopadhyayMikayel SamvelyanMinqi JiangRobert Tjarko LangeShimon WhitesonBruno LacerdaNick HawesTim RocktäschelChris LuJakob Nicolaus FoersterPublished in: CoRR (2023)
Keyphrases
- multi agent
- reinforcement learning
- multi agent environments
- cooperative
- multi agent systems
- learning agents
- intelligent agents
- data sets
- multi agent architecture
- agent oriented
- model free
- multiagent systems
- real world
- state space
- case study
- genetic algorithm
- team formation
- optimal policy
- autonomous agents
- function approximation
- multiple agents
- highly dynamic
- cooperative agents
- real time
- partially observable domains