Guide Your Agent with Adaptive Multimodal Rewards.
Changyeon KimYounggyo SeoHao LiuLisa LeeJinwoo ShinHonglak LeeKimin LeePublished in: CoRR (2023)
Keyphrases
- multi agent systems
- multi agent
- agent architecture
- decision making
- multiple agents
- multi modal
- dynamic environments
- agent model
- multiagent systems
- autonomous agents
- interacting agents
- learning capabilities
- software agents
- reinforcement learning
- human computer interaction
- reward function
- neural network
- intelligent agents
- hidden markov models
- current situation
- agent systems
- cooperating agents
- multiarmed bandit