Back to Search
Start Over
Single Trajectory Learning: Exploration Versus Exploitation
- Source :
- International Journal of Pattern Recognition and Artificial Intelligence. 32:1859009
- Publication Year :
- 2018
- Publisher :
- World Scientific Pub Co Pte Lt, 2018.
-
Abstract
- In reinforcement learning (RL), the exploration/exploitation (E/E) dilemma is a very crucial issue, which can be described as searching between the exploration of the environment to find more profitable actions, and the exploitation of the best empirical actions for the current state. We focus on the single trajectory RL problem where an agent is interacting with a partially unknown MDP over single trajectories, and try to deal with the E/E in this setting. Given the reward function, we try to find a good E/E strategy to address the MDPs under some MDP distribution. This is achieved by selecting the best strategy in mean over a potential MDP distribution from a large set of candidate strategies, which is done by exploiting single trajectories drawn from plenty of MDPs. In this paper, we mainly make the following contributions: (1) We discuss the strategy-selector algorithm based on formula set and polynomial function. (2) We provide the theoretical and experimental regret analysis of the learned strategy under an given MDP distribution. (3) We compare these methods with the “state-of-the-art” Bayesian RL method experimentally.
- Subjects :
- Polynomial
Computer science
business.industry
Regret
02 engineering and technology
Function (mathematics)
State (functional analysis)
ComputingMethodologies_ARTIFICIALINTELLIGENCE
020202 computer hardware & architecture
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Trajectory
Reinforcement learning
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Set (psychology)
Focus (optics)
Software
Subjects
Details
- ISSN :
- 17936381 and 02180014
- Volume :
- 32
- Database :
- OpenAIRE
- Journal :
- International Journal of Pattern Recognition and Artificial Intelligence
- Accession number :
- edsair.doi...........502f0af5cfbecc78328fe10275d1a68c