Reinforcement Learning in POMDPs Without Resets.
Eyal Even-DarSham M. KakadeYishay MansourPublished in: IJCAI (2005)
Keyphrases
- reinforcement learning
- partially observable markov decision processes
- function approximation
- partially observable
- markov decision processes
- state space
- reinforcement learning algorithms
- continuous state
- policy search
- optimal policy
- learning algorithm
- hidden state
- model free
- reinforcement learning methods
- supervised learning
- multi agent
- action selection
- temporal difference
- control problems
- finite state
- learning process
- partial observability
- markov decision process
- transfer learning
- machine learning
- learning problems
- mobile robot
- dynamic programming
- markov decision problems
- optimal solution
- policy gradient
- policy iteration algorithm
- policy gradient methods