Privileged Sensing Scaffolds Reinforcement Learning.
Edward S. HuJames SpringerOleh RybkinDinesh JayaramanPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference
- state space
- optimal policy
- learning outcomes
- markov decision processes
- learning environment
- sensor networks
- selective perception
- robotic control
- model free
- learning algorithm
- dynamic programming
- multi agent
- multi agent reinforcement learning
- real world
- learning problems
- computer supported
- hidden markov models
- technology enhanced
- stochastic approximation
- policy search
- neural network