On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman.
Chao GaoBilal KartalPablo Hernandez-LealMatthew E. TaylorPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- function approximation
- test bed
- exploration exploitation
- autonomous learning
- case study
- state space
- markov decision processes
- reinforcement learning algorithms
- active learning
- exploration exploitation tradeoff
- temporal difference
- model free
- optimal control
- learning algorithm
- temporal difference learning
- transfer learning
- multi agent
- balancing exploration and exploitation
- decision making
- search strategies
- robot control
- markov decision process
- learning tasks
- optimal policy
- dynamic programming
- robotic control