PIRLNav: Pretraining with Imitation and RL Finetuning for OBJECTNAV.
Ram RamrakhyaDhruv BatraErik WijmansAbhishek DasPublished in: CVPR (2023)
Keyphrases
- reinforcement learning
- model free
- reinforcement learning algorithms
- function approximation
- state space
- imitation learning
- multi agent
- learning algorithm
- learning problems
- optimal policy
- markov decision processes
- learning classifier systems
- computational models
- supervised learning
- temporal difference
- continuous domains
- function approximators
- learning agents
- temporal difference learning
- neural network