Reinforcement Learning by Guided Safe Exploration.
Qisong YangThiago D. SimãoNils JansenSimon H. TindemansMatthijs T. J. SpaanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- model based reinforcement learning
- state space
- markov decision processes
- function approximation
- autonomous learning
- learning algorithm
- reinforcement learning algorithms
- machine learning
- temporal difference
- optimal policy
- learning capabilities
- control problems
- temporal difference learning
- active learning
- learning process
- model free
- search strategies
- robot control
- markov decision problems
- supervised learning
- policy search
- multi agent
- real world
- balancing exploration and exploitation