An investigation of time reversal symmetry in reinforcement learning.
Brett BarkleyAmy ZhangDavid Fridovich-KeilPublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- model free
- function approximation
- state space
- optimal policy
- dynamic programming
- multi agent
- temporal difference
- optimal control
- direct policy search
- symmetry detection
- temporal difference learning
- action space
- control problems
- action selection
- learning problems
- artificial intelligence
- learning algorithm
- markov decision processes
- least squares
- evolutionary algorithm
- partially observable
- learning process
- robot control
- information systems
- control policy
- transition model
- active exploration
- medial axes
- neural network