On Hard Exploration for Reinforcement Learning: A Case Study in Pommerman.
Chao GaoBilal KartalPablo Hernandez-LealMatthew E. TaylorPublished in: AIIDE (2019)
Keyphrases
- reinforcement learning
- active exploration
- action selection
- exploration strategy
- model based reinforcement learning
- exploration exploitation
- function approximation
- autonomous learning
- case study
- reinforcement learning algorithms
- databases
- robotic control
- temporal difference
- state space
- optimal control
- model free
- dynamic programming
- multi agent
- database
- fitted q iteration
- exploration exploitation tradeoff
- test bed
- optimal policy
- active learning
- interactive exploration
- website
- information retrieval
- machine learning
- neural network