Barrier Functions Inspired Reward Shaping for Reinforcement Learning.
Nilaksh NilakshAbhishek RanjanShreenabh AgrawalAayush JainPushpak JagtapShishir KolathayaPublished in: CoRR (2024)
Keyphrases
- reward shaping
- reinforcement learning
- reinforcement learning algorithms
- complex domains
- state space
- function approximation
- markov decision problems
- learning process
- machine learning
- temporal difference
- model free
- markov decision processes
- learning agent
- linear program
- dynamical systems
- decision makers
- mobile robot
- knowledge base
- decision making
- transition model
- policy search
- neural network