An Approach to Optimize Replay Buffer in Value-Based Reinforcement Learning.
Baicheng ChenTianhan GaoQingwei MiPublished in: SoSE (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- machine learning
- information systems
- control problems
- action selection
- markov decision processes
- policy search
- buffer size
- transfer learning
- least squares
- state space
- optimal policy
- real time
- model free
- reinforcement learning algorithms
- learning capabilities
- dynamic programming
- function approximators
- virtual memory
- learning process
- multi agent
- relational reinforcement learning