Coupling Effect of Exploration Rate and Learning Rate for Optimized Scaled Reinforcement Learning.
Smriti GuptaSabita PalKundan KumarKuntal GhoshPublished in: SN Comput. Sci. (2023)
Keyphrases
- learning rate
- reinforcement learning
- learning algorithm
- convergence rate
- hidden layer
- action selection
- active exploration
- error function
- exploration strategy
- rapid convergence
- convergence speed
- function approximation
- multilayer neural networks
- weight vector
- activation function
- reinforcement learning algorithms
- markov decision processes
- adaptive learning rate
- state space
- optimal policy
- evolutionary algorithm
- convergence theorem
- model free
- machine learning
- linear program