Reflexion: language agents with verbal reinforcement learning.
Noah ShinnFederico CassanoAshwin GopinathKarthik NarasimhanShunyu YaoPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- robotic agents
- agent programming
- action selection
- multi agent systems
- multiagent systems
- multi agent reinforcement learning
- dynamic logic
- agent communication
- single agent
- agent receives
- oriented programming
- partial observability
- multi agent environments
- multiple agents
- intelligent agents
- reinforcement learning agents
- autonomous agents
- cooperative
- learning agent
- agent systems
- agent oriented programming language
- multiagent learning
- reinforcement learning algorithms
- natural language
- software agents
- machine learning
- decision making
- multiagent reinforcement learning
- incomplete information
- function approximation
- agent technology
- learning capabilities
- learned knowledge
- language learning
- markov decision processes
- evolutionary learning
- temporal difference
- computer programs
- state space
- programming language
- coalition formation
- optimal policy
- model free
- dynamic environments
- resource allocation
- complex environments
- robocup soccer
- artificial agents
- speech acts