Barrier Functions Inspired Reward Shaping for Reinforcement Learning.
NilakshAbhishek RanjanShreenabh AgrawalAayush JainPushpak JagtapShishir KolathayaPublished in: ICRA (2024)
Keyphrases
- reward shaping
- reinforcement learning
- reinforcement learning algorithms
- complex domains
- state space
- markov decision problems
- learning algorithm
- multi agent
- markov decision processes
- function approximation
- model free
- optimal control
- policy search
- dynamic programming
- partially observable
- decision making
- machine learning
- dynamical systems
- decision theoretic
- temporal difference
- knowledge base