Deep Reinforcement Learning With Macro-Actions.
Ishan P. DurugkarClemens RosenbaumStefan DernbachSridhar MahadevanPublished in: CoRR (2016)
Keyphrases
- macro actions
- reinforcement learning
- markov decision processes
- state space
- function approximation
- model free
- learning algorithm
- reinforcement learning algorithms
- optimal policy
- learning process
- temporal difference
- learned knowledge
- machine learning
- multi agent
- markov chain
- partially observable
- markov decision process
- markov decision problems
- dynamic programming
- action selection
- search space
- reinforcement learning methods
- planning under uncertainty