Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning.
Piyush GuptaVaibhav SrivastavaPublished in: CoRR (2022)
Keyphrases
- exploration exploitation tradeoff
- reinforcement learning
- active exploration
- function approximation
- relevance feedback
- exploration strategy
- objective function
- action selection
- model based reinforcement learning
- deterministic domains
- autonomous learning
- exploration exploitation
- markov decision processes
- search capabilities
- reinforcement learning algorithms
- state space
- multi agent
- model free
- dynamic programming
- learning algorithm
- robotic control
- partially observable markov decision processes
- action space
- reinforcement learning methods
- initially unknown
- planning problems
- finite state automaton
- search engine