An empirical analysis of value function-based and policy search reinforcement learning.
Shivaram KalyanakrishnanPeter StonePublished in: AAMAS (2) (2009)
Keyphrases
- policy search
- reinforcement learning
- policy gradient
- function approximators
- reinforcement learning algorithms
- continuous state
- dynamic programming
- state space
- continuous action
- markov decision processes
- function approximation
- model free
- state action
- temporal difference
- reward function
- partially observable markov decision processes
- transfer learning
- approximation methods
- machine learning
- reinforcement learning methods