Cost effective transfer of reinforcement learning policies.
Orel LavieAsaf ShabtaiGilad KatzPublished in: Expert Syst. Appl. (2024)
Keyphrases
- cost effective
- reinforcement learning
- optimal policy
- transfer learning
- policy search
- control policies
- markov decision process
- low cost
- function approximation
- reward function
- state space
- cost effectiveness
- reinforcement learning agents
- markov decision processes
- control policy
- fitted q iteration
- partially observable markov decision processes
- markov decision problems
- hierarchical reinforcement learning
- machine learning
- dynamic programming
- policy gradient methods
- reinforcement learning algorithms
- previously learned
- infinite horizon
- model free
- action space
- data center
- long run
- multi agent
- multiagent reinforcement learning
- long term
- multi agent reinforcement learning
- intrusion detection
- information and communication technologies
- temporal difference
- decision problems
- function approximators
- optimal control
- knowledge transfer
- learning process
- finite state
- real time