Reinforcement Learning with Reward Shaping and Hybrid Exploration in Sparse Reward Scenes.
Yulong YangWeihua CaoLinwei GuoChao GanMin WuPublished in: ICPS (2023)
Keyphrases
- reward shaping
- reinforcement learning
- complex domains
- reinforcement learning algorithms
- action selection
- state space
- function approximation
- reward function
- learning algorithm
- markov decision processes
- model free
- markov decision problems
- machine learning
- transfer learning
- markov decision process
- case based reasoning
- learning capabilities
- policy iteration
- decision processes