Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints.
Dohyeong KimKyungjae LeeSonghwai OhPublished in: NeurIPS (2023)
Keyphrases
- multiple constraints
- reinforcement learning
- trust model
- co occurrence
- trust evaluation
- function approximation
- image segmentation
- model free
- multi agent
- reinforcement learning algorithms
- temporal difference
- state space
- social capital
- markov decision processes
- dynamic programming
- learning process
- learning algorithm
- robotic control
- real robot
- trust management
- temporal difference learning
- virtual communities
- website design
- learning problems
- hidden markov models