Maze Solver: A Federated Reinforcement Learning Approach.
Aayush SharmaHarjeet KaurDeepak PrasharPublished in: ICCCNT (2023)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- digital libraries
- learning algorithm
- temporal difference
- temporal difference learning
- state space
- active learning
- optimal policy
- model free
- markov decision processes
- learning process
- real time
- evaluation function
- data sources
- dynamic programming
- search space
- learning agent
- action space
- multi agent
- stochastic approximation