Personalized Reinforcement Learning with a Budget of Policies.
Dmitry IvanovOmer Ben-PoratPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- markov decision processes
- fitted q iteration
- state space
- adaptive learning
- reward function
- control policy
- reinforcement learning agents
- partially observable markov decision processes
- hierarchical reinforcement learning
- function approximation
- markov decision problems
- cooperative multi agent systems
- policy gradient methods
- e learning
- infinite horizon
- dynamic programming
- macro actions
- user modeling
- total reward
- learning algorithm
- decision problems
- partially observable
- multi agent
- robotic control
- long run
- optimal control
- reinforcement learning algorithms
- context aware
- user profiles
- finite state
- personalized services
- decentralized control
- transition model
- multiagent reinforcement learning
- learning problems
- management policies
- continuous state
- personalized information
- supervised learning
- temporal difference
- machine learning