Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning.
Hugo Caselles-DupréOlivier SigaudMohamed ChetouaniPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- natural language
- english language
- language learning
- programming language
- learning algorithm
- dynamic programming
- reinforcement learning algorithms
- data mining
- operational semantics
- language processing
- temporal difference learning
- databases
- object oriented programming
- temporal difference
- function approximation
- markov decision processes
- state space
- search engine