Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates
This enables more autonomous learning for robotics, though it is incremental as it builds on existing deep reinforcement learning methods.
The paper tackled the challenge of applying deep reinforcement learning to complex 3D robotic manipulation tasks, demonstrating that an off-policy algorithm can efficiently train neural network policies on real robots without human demonstrations, reducing training times through asynchronous parallelization across multiple robots.
Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on off-policy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.