Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
- URL: http://arxiv.org/abs/2004.14404v2
- Date: Sat, 23 May 2020 01:42:24 GMT
- Title: Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
- Authors: Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, Sergey Levine,
Eugen Solowjow
- Abstract summary: We study how to use meta-reinforcement learning to solve the bulk of the problem in simulation.
We demonstrate our approach by training an agent to successfully perform challenging real-world insertion tasks.
- Score: 70.56451186797436
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Robotic insertion tasks are characterized by contact and friction mechanics,
making them challenging for conventional feedback control methods due to
unmodeled physical effects. Reinforcement learning (RL) is a promising approach
for learning control policies in such settings. However, RL can be unsafe
during exploration and might require a large amount of real-world training
data, which is expensive to collect. In this paper, we study how to use
meta-reinforcement learning to solve the bulk of the problem in simulation by
solving a family of simulated industrial insertion tasks and then adapt
policies quickly in the real world. We demonstrate our approach by training an
agent to successfully perform challenging real-world insertion tasks using less
than 20 trials of real-world experience. Videos and other material are
available at https://pearl-insertion.github.io/
Related papers
- REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous
Manipulation [61.7171775202833]
We introduce an efficient system for learning dexterous manipulation skills withReinforcement learning.
The main idea of our approach is the integration of recent advances in sample-efficient RL and replay buffer bootstrapping.
Our system completes the real-world training cycle by incorporating learned resets via an imitation-based pickup policy.
arXiv Detail & Related papers (2023-09-06T19:05:31Z) - Accelerating Robot Learning of Contact-Rich Manipulations: A Curriculum
Learning Study [4.045850174820418]
This paper presents a study for accelerating robot learning of contact-rich manipulation tasks based on Curriculum Learning combined with Domain Randomization (DR)
We tackle complex industrial assembly tasks with position-controlled robots, such as insertion tasks.
Results also show that even when training only in simulation with toy tasks, our method can learn policies that can be transferred to the real-world robot.
arXiv Detail & Related papers (2022-04-27T11:08:39Z) - Practical Imitation Learning in the Real World via Task Consistency Loss [18.827979446629296]
This paper introduces a self-supervised loss that encourages sim and real alignment both at the feature and action-prediction levels.
We achieve 80% success across ten seen and unseen scenes using only 16.2 hours of teleoperated demonstrations in sim and real.
arXiv Detail & Related papers (2022-02-03T21:43:06Z) - Accelerating Robotic Reinforcement Learning via Parameterized Action
Primitives [92.0321404272942]
Reinforcement learning can be used to build general-purpose robotic systems.
However, training RL agents to solve robotics tasks still remains challenging.
In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy.
We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
arXiv Detail & Related papers (2021-10-28T17:59:30Z) - Robotic Surgery With Lean Reinforcement Learning [0.8258451067861933]
We describe adding reinforcement learning support to the da Vinci Skill Simulator.
We teach an RL-based agent to perform sub-tasks in the simulator environment, using either image or state data.
We tackle the sample inefficiency of RL using a simple-to-implement system which we term hybrid-batch learning (HBL)
arXiv Detail & Related papers (2021-05-03T16:52:26Z) - A Framework for Efficient Robotic Manipulation [79.10407063260473]
We show that a single robotic arm can learn sparse-reward manipulation policies from pixels.
We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
arXiv Detail & Related papers (2020-12-14T22:18:39Z) - AWAC: Accelerating Online Reinforcement Learning with Offline Datasets [84.94748183816547]
We show that our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience.
Our results show that incorporating prior data can reduce the time required to learn a range of robotic skills to practical time-scales.
arXiv Detail & Related papers (2020-06-16T17:54:41Z) - Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera [58.720142291102135]
We use a simulator to learn the peg-hole insertion problem and then transfer the learned model to the real robot.
We show that the transferred policy, which only takes RGB-D and joint information (proprioception) can perform well on the real robot.
arXiv Detail & Related papers (2020-05-29T05:58:54Z) - Deep Adversarial Reinforcement Learning for Object Disentangling [36.66974848126079]
We present a novel adversarial reinforcement learning (ARL) framework for disentangling waste objects.
The ARL framework utilizes an adversary, which is trained to steer the original agent, the protagonist, to challenging states.
We show that our method can generalize from training to test scenarios by training an end-to-end system for robot control to solve a challenging object disentangling task.
arXiv Detail & Related papers (2020-03-08T13:20:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.