Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction.
Fengda ZhuXiaojun ChangRunhao ZengMingkui TanPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- multi agent
- action selection
- model based reinforcement learning
- function approximation
- exploration exploitation
- model free
- autonomous learning
- exploration exploitation tradeoff
- reinforcement learning algorithms
- state space
- learning algorithm
- markov decision processes
- temporal difference learning
- search strategies
- optimal policy
- machine learning
- learning problems
- error correction
- visualization tool
- evolutionary algorithm
- learning process
- case study
- robotic control
- data sets