PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav.
Ram RamrakhyaDhruv BatraErik WijmansAbhishek DasPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- reinforcement learning algorithms
- learning algorithm
- markov decision processes
- multi agent
- optimal policy
- function approximation
- learned knowledge
- model free
- supervised learning
- transfer learning
- learning problems
- rl algorithms
- temporal difference
- action selection
- learning process
- mobile robot
- dynamic programming
- machine learning
- neural network
- temporal difference learning
- reinforcement learning methods
- database