Reinforcement Learning by Comparing Immediate Reward
Punit PandeyDeepshikha PandeyShishir KumarPublished in: CoRR (2010)
Keyphrases
- data mining
- reinforcement learning
- machine learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- markov decision processes
- transfer learning
- reward function
- multi agent
- dynamic programming
- learning problems
- learning agent
- learning process
- model free
- eligibility traces
- average reward
- total reward
- decision making
- reinforcement learning methods
- reward shaping
- genetic algorithm
- temporal difference
- action selection
- real time
- supervised learning