Funnel-Based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning.
Naman SaxenaSandeep GorantlaPushpak JagtapPublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- temporal logic
- reward shaping
- reinforcement learning
- complex domains
- model checking
- reinforcement learning algorithms
- modal logic
- transfer learning
- state space
- function approximation
- belief revision
- reward function
- multi agent
- markov decision problems
- verification method
- linear temporal logic
- machine learning
- model free
- learning algorithm
- markov decision processes
- linear programming
- markov decision process
- symbolic model checking
- temporally extended