Page 116 |
Save page Remove page | Previous | 116 of 151 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
meta-loss network to perform effective policy updates in a reinforcement learning scenario. To
apply our ML3 framework, we replace the optimizee f from the previous section with a stochastic
policy (aSs). We present two applications of ML3 to RL.
ML3 for Model-Based Reinforcement Learning
Model-based RL (MBRL) attempts to learn a policy by first learning a dynamic model P.
Intuitively, if the model P is accurate, we can use it to optimize the policy parameters . As
we typically do not know the dynamics model a-priori, MBRL algorithms iterate between using
the current approximate dynamics model P, to optimize the policy such that it maximizes
the reward R under P, then use the optimized policy to collect more data which is used to
update the model P. In this context, we aim to learn a loss function that is used to optimize policy
parameters through our meta-networkM.
Similar to the supervised learning setting we use current meta-parameters to optimize
policy parameters under the current dynamics model P: new = − © M ( ; g) , where
= (s0; a0; : : : ; sT ; aT ) is the sampled trajectory and the variable g captures some task-specific
information, such as the goal state of the agent. To optimize we again need to define a task
loss, which in the MBRL setting can be defined as LT (g; new) = −E new;P [Rg( new)], denoting
the reward that is achieved under the current dynamics model P. To update , we compute
the gradient of the task loss LT wrt. , which involves differentiating all the way through the
reward function, dynamics model and the policy that was updated using the meta-lossM . The
pseudo-code in Algorithm 3 illustrates the MBRL learning loop. In Algorithm 5, we show the
policy optimization procedure during meta-test time. Notably, we have found that in practice, the
model of the dynamics P is not needed anymore for policy optimization at meta-test time. The
101
Object Description
| Title | Data scarcity in robotics: leveraging structural priors and representation learning |
| Author | Molchanov, Artem |
| Author email | a.molchanov86@gmail.com;molchano@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2020-05-11 |
| Date submitted | 2020-08-11 |
| Date approved | 2020-08-11 |
| Restricted until | 2020-08-11 |
| Date published | 2020-08-11 |
| Advisor (committee chair) | Sukhatme, Gaurav Suhas |
| Advisor (committee member) |
Ayanian, Nora Culbertson, Heather Gupta, Satyandra K. |
| Abstract | Recent advances in Artificial Intelligence have benefited significantly from access to large pools of data accompanied in many cases by labels, ground truth values, or perfect demonstrations. In robotics, however, such data are scarce or absent completely. Overcoming this issue is a major barrier to move robots from structured laboratory settings to the unstructured real world. In this dissertation, by leveraging structural priors and representation learning, we provide several solutions when data required to operate robotics systems is scarce or absent. ❧ In the first part of this dissertation we study sensory feedback scarcity. We show how to use high-dimensional alternative sensory modalities to extract data when primary sensory sources are absent. In a robot grasping setting, we address the problem of contact localization and solve it using multi-modal tactile feedback as the alternative source of information. We leverage multiple tactile modalities provided by electrodes and hydro-acoustic sensors to structure the problem as spatio-temporal inference. We employ the representational power of neural networks to acquire the complex mapping between tactile sensors and the contact locations. We also investigate scarce feedback due to the high cost of measurements. We study this problem in a challenging field robotics setting where multiple severely underactuated aquatic vehicles need to be coordinated. We show how to leverage collaboration among the vehicles and the spatio-temporal smoothness of the ocean currents as a prior to densify feedback about ocean currents in order to acquire better controllability. ❧ In the second part of this dissertation, we investigate scarcity of the data related to the desired task. We develop a method to efficiently leverage simulated dynamics priors to perform sim-to-real transfer of a control policy when no data about the target system is available. We investigate this problem in the scenario of sim-to-real transfer of low-level stabilizing quadrotor control policies. We demonstrate that we can learn robust policies in simulation and transfer them to the real system while acquiring no samples from the real quadrotor. Finally, we consider the general problem of learning a model with a very limited number of samples using meta-learned losses. We show how such losses can encode a prior structure about families of tasks to create well-behaved loss landscapes for efficient model optimization. We demonstrate the efficiency of our approach for learning policies and dynamics models in multiple robotics settings. |
| Keyword | robotics; machine learning; artificial intelligence |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m |
| Contributing entity | University of Southern California |
| Rights | Molchanov, Artem |
| Physical access | The author retains rights to his/her dissertation, thesis or other graduate work according to U.S. copyright law. Electronic access is being provided by the USC Libraries in agreement with the author, as the original true and official version of the work, but does not grant the reader permission to use the work if the desired use is covered by copyright. It is the author, as rights holder, who must provide use permission if such use is covered by copyright. The original signature page accompanying the original submission of the work to the USC Libraries is retained by the USC Libraries and a copy of it may be obtained by authorized requesters contacting the repository e-mail address given. |
| Repository name | University of Southern California Digital Library |
| Repository address | USC Digital Library, University of Southern California, University Park Campus MC 7002, 106 University Village, Los Angeles, California 90089-7002, USA |
| Repository email | cisadmin@lib.usc.edu |
| Filename | etd-MolchanovA-8923.pdf |
| Archival file | Volume13/etd-MolchanovA-8923.pdf |
Description
| Title | Page 116 |
| Full text | meta-loss network to perform effective policy updates in a reinforcement learning scenario. To apply our ML3 framework, we replace the optimizee f from the previous section with a stochastic policy (aSs). We present two applications of ML3 to RL. ML3 for Model-Based Reinforcement Learning Model-based RL (MBRL) attempts to learn a policy by first learning a dynamic model P. Intuitively, if the model P is accurate, we can use it to optimize the policy parameters . As we typically do not know the dynamics model a-priori, MBRL algorithms iterate between using the current approximate dynamics model P, to optimize the policy such that it maximizes the reward R under P, then use the optimized policy to collect more data which is used to update the model P. In this context, we aim to learn a loss function that is used to optimize policy parameters through our meta-networkM. Similar to the supervised learning setting we use current meta-parameters to optimize policy parameters under the current dynamics model P: new = − © M ( ; g) , where = (s0; a0; : : : ; sT ; aT ) is the sampled trajectory and the variable g captures some task-specific information, such as the goal state of the agent. To optimize we again need to define a task loss, which in the MBRL setting can be defined as LT (g; new) = −E new;P [Rg( new)], denoting the reward that is achieved under the current dynamics model P. To update , we compute the gradient of the task loss LT wrt. , which involves differentiating all the way through the reward function, dynamics model and the policy that was updated using the meta-lossM . The pseudo-code in Algorithm 3 illustrates the MBRL learning loop. In Algorithm 5, we show the policy optimization procedure during meta-test time. Notably, we have found that in practice, the model of the dynamics P is not needed anymore for policy optimization at meta-test time. The 101 |
