Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning.
Lev GrossmanBrian PlancherPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- human perception
- learning algorithm
- machine learning
- run length
- temporal difference learning
- state space
- reinforcement learning algorithms
- robotic control
- control problems
- temporal difference
- model free
- markov decision processes
- optimal policy
- transfer learning
- supervised learning
- dynamic programming
- search algorithm
- artificial intelligence
- stochastic approximation
- relational reinforcement learning
- data sets