Timezone: »

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention
Abhishek Gupta · Justin Yu · Tony Z. Zhao · Vikash Kumar · Aaron Rovinsky · Kelvin Xu · Thomas Devlin · Sergey Levine

Reinforcement Learning (RL) algorithms can in principle acquire complex robotic skills by learning from large amounts of data in the real world, collected via trial and error. However, most RL algorithms use a carefully engineered setup in order to collect data, requiring human supervision and intervention to provide episodic resets. This is particularly evident in challenging robotics problems, such as dexterous manipulation. To make data collection scalable, such applications require reset-free algorithms that are able to learn autonomously, without explicit instrumentation or human intervention. Most prior work in this area handles single-task learning. However, we might also want robots that can perform large repertoires of skills. At first, this would appear to only make the problem harder. However, the key observation we make in this work is that an appropriately chosen multi-task RL setting actually alleviates the reset-free learning challenge, with minimal additional machinery required. In effect, solving a multi-task problem can directly solve the reset-free problem since different combinations of tasks can serve to perform resets for other tasks. By learning multiple tasks together and appropriately sequencing them, we can effectively learn all of the tasks together reset-free. This type of multi-task learning can effectively scale reset-free learning schemes to much more complex problems, as we demonstrate in our experiments. We propose a simple scheme for multi-task learning that tackles the reset-free learning problem, and show its effectiveness at learning to solve complex dexterous manipulation tasks in both hardware and simulation without any explicit resets. This work shows the ability to learn dexterous manipulation behaviors in the real world with RL without any human intervention.

Author Information

Abhishek Gupta (UC Berkeley)
Justin Yu (Berkeley)
Tony Z. Zhao (UC Berkeley)
Vikash Kumar (Univ. Of Washington)
Aaron Rovinsky (UC Berkeley)
Kelvin Xu (University of California, Berkeley)
Thomas Devlin (UC Berkeley)
Sergey Levine (University of California, Berkeley)

More from the Same Authors