An official website of the United States government
Hierarchical reinforcement learning (HRL) is only effective for long-horizon problems when high-level skills can be reliably sequentially executed. Unfortunately, learning reliably composable skills is difficult, because all the components of every skill are constantly changing during learning. We propose three methods for improving the composability of learned skills: representing skill initiation regions using a combination of pessimistic and optimistic classifiers; learning re-targetable policies that are robust to non-stationary subgoal regions; and learning robust option policies using model-based RL. We test these improvements on four sparse-reward maze navigation tasks involving a simulated quadrupedal robot. Each method successively improves the robustness of a baseline skill discovery method, substantially outperforming state-of-the-art flat and hierarchical methods.
more »
« less
Data-Oriented State Space Discretization for Crowdsourced Robot Learning of Physical Skills
Abstract This work discusses a crowdsourced learning scheme for robot physical intelligence. Using a large amount of data from crowdsourced mentors, the scheme allows robots to synthesize new physical skills that are never demonstrated or only partially demonstrated without heavy re-training. The learning scheme features a data management method to sustainably manage continuously collected data and a growing knowledge library. The method is validated using a simulated challenge of solving a bottle puzzle. The learning scheme aims at realizing ubiquitous robot learning of physical skills and has the potential of automating many demanding tasks that are currently hard to robotize.
more »
« less
- Award ID(s):
- 1944069
- PAR ID:
- 10225329
- Date Published:
- Journal Name:
- ASME Letters in Dynamic Systems and Control
- Volume:
- 1
- Issue:
- 2
- ISSN:
- 2689-6117
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Hierarchical reinforcement learning (HRL) is only effective for long-horizon problems when high-level skills can be reliably sequentially executed. Unfortunately, learning reliably composable skills is difficult, because all the components of every skill are constantly changing during learning. We propose three methods for improving the composability of learned skills: representing skill initiation regions using a combination of pessimistic and optimistic classifiers; learning re-targetable policies that are robust to non-stationary subgoal regions; and learning robust option policies using model-based RL. We test these improvements on four sparse-reward maze navigation tasks involving a simulated quadrupedal robot. Each method successively improves the robustness of a baseline skill discovery method, substantially outperforming state-of-the-art flat and hierarchical methods.more » « less
-
Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must typically be bootstrapped using human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly outperforms starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration.more » « less
-
This paper presents a visual servoing method for controlling a robot in the configuration space by purely using its natural features. We first created a data collection pipeline that uses camera intrinsics, extrinsics, and forward kinematics to generate 2D projections of a robot's joint locations (keypoints) in image space. Using this pipeline, we are able to collect large sets of real-robot data, which we use to train realtime keypoint detectors. The inferred keypoints from the trained model are used as control features in an adaptive visual servoing scheme that estimates, in runtime, the Jacobian relating the changes of the keypoints and joint velocities. We compared the 2D configuration control performance of this method to the skeleton-based visual servoing method (the only other algorithm for purely vision-based configuration space visual servoing), and demonstrated that the keypoints provide more robust and less noisy features, which result in better transient response. We also demonstrate the first vision-based 3D configuration space control results in the literature, and discuss its limitations. Our data collection pipeline is available at https://github.com/JaniC-WPI/KPDataGenerator.git which can be utilized to collect image datasets and train realtime keypoint detectors for various robots and environments.more » « less
-
Abstract The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1115/1.4047961
