Influencing Reinforcement Learning through Natural Language Guidance.
Tasmia TasrinMd Sultan Al NahianHabarakadage PereraBrent HarrisonPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- natural language
- machine learning
- function approximation
- natural language processing
- semantic analysis
- learning algorithm
- reinforcement learning algorithms
- robotic control
- natural language generation
- temporal difference
- knowledge representation
- optimal policy
- natural language interface
- multi agent
- state space
- model free
- neural network
- semantic interpretation
- dialogue system
- natural language text
- optimal control
- information extraction
- action selection
- markov decision processes
- partially observable
- semantic representation
- data mining
- machine translation
- question answering
- formal language
- temporal difference learning
- reinforcement learning methods
- multi agent reinforcement learning
- natural language sentences
- least squares