Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning.
Lev GrossmanBrian PlancherPublished in: ICRA (2024)
Keyphrases
- reinforcement learning
- function approximation
- model free
- machine learning
- temporal difference
- action selection
- human perception
- state space
- supervised learning
- optimal policy
- markov decision processes
- dynamic programming
- multi agent
- control system
- learning process
- real time
- reinforcement learning algorithms
- run length
- reinforcement learning methods
- stochastic approximation
- autonomous learning
- relational reinforcement learning