Partially observable environment estimation with uplift inference for reinforcement learning based recommendation.
Wenjie ShangQingyang LiZhiwei (Tony) QinYang YuYiping MengJieping YePublished in: Mach. Learn. (2021)
Keyphrases
- partially observable
- reinforcement learning
- state space
- markov decision processes
- partially observable markov decision process
- decision problems
- initially unknown
- partial observability
- dynamical systems
- partially observable domains
- markov decision problems
- partially observable environments
- action models
- function approximation
- partial observations
- infinite horizon
- reward function
- reinforcement learning algorithms
- hidden state
- collaborative filtering
- decision theoretic
- mobile robot
- model free
- optimal policy
- learning agent
- optimal control
- planning problems
- transfer learning
- markov decision process
- dynamic environments
- lower bound