GLIDE-RL: Grounded Language Instruction through DEmonstration in RL.
Chaitanya KharyalSai Krishna GottipatiTanmay Kumar SinhaSrijita DasMatthew E. TaylorPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- autonomous learning
- programming language
- multi agent
- model free
- reinforcement learning algorithms
- learning algorithm
- natural language
- language learning
- partially observable domains
- control policy
- action space
- temporal difference
- action selection
- transfer learning
- optimal policy
- object oriented
- multimedia