What makes generalization hard for imitation learning in visual robotic
...
Large transformer models trained on diverse datasets have shown a remark...
A long-term goal of reinforcement learning is to design agents that can
...
Reinforcement learning (RL) agents need to be robust to variations in
sa...
Learning in multi-agent environments is difficult due to the non-station...
Multi-task learning ideally allows robots to acquire a diverse repertoir...
Seamlessly interacting with humans or robots is hard because these agent...
As humans, our goals and our environment are persistently changing throu...
Learning predictive models from interaction with the world allows an age...
Machine learning techniques have enabled robots to learn narrow, yet com...
Deep reinforcement learning (RL) algorithms can learn complex robotic sk...
Reinforcement learning and planning methods require an objective or rewa...
Humans and animals are capable of learning a new behavior by observing o...