Deep Variational Reinforcement Learning for POMDPs.
Maximilian IglLuisa M. ZintgrafTuan Anh LeFrank WoodShimon WhitesonPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- partially observable markov decision processes
- function approximation
- state space
- policy search
- partially observable
- markov decision processes
- reinforcement learning algorithms
- continuous state
- image segmentation
- optimal policy
- machine learning
- multi agent
- optical flow
- learning algorithm
- model free
- partially observable environments
- dynamic programming
- temporal difference
- belief state
- transfer learning
- policy gradient
- policy iteration algorithm
- markov decision problems
- average reward
- function approximators
- long run
- learning problems
- supervised learning
- learning process