Embodied control requires agents to leverage multi-modal pre-training to...
Diffusion models have demonstrated their powerful generative capability ...
Placement is an essential task in modern chip design, aiming at placing
...
The latent world model provides a promising way to learn policies in a
c...
Adapting to the changes in transition dynamics is essential in robotic
a...
Unsupervised reinforcement learning (URL) poses a promising paradigm to ...
Transformer has achieved great successes in learning vision and language...
Unsupervised contrastive learning for indoor-scene point clouds has achi...
Partially Observable Markov Decision Process (POMDP) provides a principl...
Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based...
One of the key challenges in visual Reinforcement Learning (RL) is to le...
Safety is essential for reinforcement learning (RL) applied in the real
...
Safety is essential for reinforcement learning (RL) applied in real-worl...
Reinforcement learning has shown great potential in developing high-leve...
Safety constraints are essential for reinforcement learning (RL) applied...
Reinforcement learning (RL) methods often rely on massive exploration da...