Generalization Across Observation Shifts in Reinforcement Learning.
Anuj MahajanAmy ZhangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- robotic control
- state space
- real time
- reinforcement learning algorithms
- temporal difference
- function approximation
- multi agent
- policy gradient
- data sets
- neural network
- optimal policy
- markov decision processes
- action selection
- optimal control
- learning machines
- model free
- database
- objective function
- control problems
- machine learning
- least squares
- learning algorithm
- dynamic programming
- expert systems
- website