Transformable Gaussian Reward Function for Socially Aware Navigation Using Deep Reinforcement Learning.
Jinyeob KimSumin KangSungwoo YangBeomjoon KimJargalbaatar YuraDong Han KimPublished in: Sensors (2024)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- state space
- optimal policy
- multi agent
- policy search
- partially observable
- markov decision process
- inverse reinforcement learning
- maximum likelihood
- function approximation
- multiple agents
- transition probabilities
- learning agent
- transition model
- generative model
- model free
- machine learning
- state variables
- dynamic programming
- hierarchical reinforcement learning
- function approximators