Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Puri, Ujjwal"'
On-policy reinforcement learning (RL) has become a popular framework for solving sequential decision problems due to its computational efficiency and theoretical simplicity. Some on-policy methods guarantee every policy update is constrained to a tru
Externí odkaz:
http://arxiv.org/abs/2312.05405
In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great promise of con
Externí odkaz:
http://arxiv.org/abs/2110.10255
We explore possible methods for multi-task transfer learning which seek to exploit the shared physical structure of robotics tasks. Specifically, we train policies for a base set of pre-training tasks, then experiment with adapting to new off-distrib
Externí odkaz:
http://arxiv.org/abs/2106.13237
Publikováno v:
AIP Conference Proceedings; 2024, Vol. 3075 Issue 1, p1-19, 19p