Imitation learning from observation with automatic discount scheduling
Humans often acquire new skills through observation and imitation. For robotic agents,
learning from the plethora of unlabeled video demonstration data available on the Internet …
learning from the plethora of unlabeled video demonstration data available on the Internet …
Visual Imitation Learning with Calibrated Contrastive Representation
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-
dimensional states and actions. However, challenges arise in handling visual states due to …
dimensional states and actions. However, challenges arise in handling visual states due to …
MRIC: Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation
B He, Y Li - arXiv preprint arXiv:2404.18464, 2024 - arxiv.org
Accurately simulating diverse behaviors of heterogeneous agents in various scenarios is
fundamental to autonomous driving simulation. This task is challenging due to the multi …
fundamental to autonomous driving simulation. This task is challenging due to the multi …
Mastering Pixel-Based Reinforcement Learning via Positive Unlabeled Policy-Guided Contrast
Real-world reinforcement learning has received a significant amount of attention very
recently. A fundamental yet challenging problem in this learning paradigm is perceiving real …
recently. A fundamental yet challenging problem in this learning paradigm is perceiving real …