Diffusion-Reward Adversarial Imitation Learning.
Chun-Mao LaiHsiang-Chun WangPing-Chun HsiehYu-Chiang Frank WangMin-Hung ChenShao-Hua SunPublished in: CoRR (2024)
Keyphrases
- imitation learning
- reinforcement learning
- multi agent
- robotic systems
- humanoid robot
- maximum margin
- reinforcement learning methods
- markov decision processes
- function approximation
- state space
- dynamic programming
- transfer learning
- multi modal
- machine learning
- vision system
- long run
- action selection
- reward function
- control problems
- learning agent
- average reward
- relational domains
- learning algorithm