Personalized Reinforcement Learning with a Budget of Policies.
Dmitry IvanovOmer Ben-PoratPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- state space
- markov decision processes
- partially observable markov decision processes
- reinforcement learning algorithms
- reinforcement learning agents
- reward function
- function approximation
- cooperative multi agent systems
- adaptive learning
- e learning
- markov decision problems
- fitted q iteration
- control policy
- hierarchical reinforcement learning
- total reward
- model free
- continuous state
- partially observable
- dynamic programming
- learning problems
- action selection
- robotic control
- macro actions
- multiagent reinforcement learning
- learning process
- multi agent reinforcement learning
- policy gradient methods
- machine learning
- average reward
- reinforcement learning methods
- temporal difference learning
- policy iteration
- average cost
- long run
- finite state
- decision problems
- collaborative filtering
- sufficient conditions
- user profiles
- transfer learning
- temporal difference
- personalized information
- user modeling
- infinite horizon