A new Potential-Based Reward Shaping for Reinforcement Learning Agent.
Babak BadnavaMona EsmaeiliNasser MozayaniPayman Zarkesh-HaPublished in: CCWC (2023)
Keyphrases
- reward shaping
- learning agent
- reinforcement learning
- reinforcement learning algorithms
- state space
- complex domains
- learning algorithm
- solving problems
- learning process
- markov decision problems
- learning capabilities
- fuzzy logic
- learning tasks
- knowledge acquisition
- agent learns
- information processing
- temporal difference