Meta-Reinforcement Learning via Language Instructions.
Zhenshan BingAlexander KochXiangtong YaoKai HuangAlois C. KnollPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- meta level
- computer programs
- language learning
- programming language
- function approximation
- natural language
- learning algorithm
- learning process
- markov decision processes
- language processing
- expert systems
- multi agent
- data sets
- optimal policy
- object oriented
- model free
- temporal difference
- specification language
- multi agent reinforcement learning
- meta reasoning