English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

State representation learning (SRL) in partially observable Markov decisionprocesses has been studied to learn abstract features of data useful for robotcontrol tasks. For SRL, acquiring domain-agnostic states is essential forachieving efficient imitation learning. Without these states, imitationlearning is hampered by domain-dependent information useless for control.However, existing methods fail to remove such disturbances from the states whenthe data from experts and agents show large domain shifts. To overcome thisissue, we propose a domain-adversarial and conditional state space model(DAC-SSM) that enables control systems to obtain domain-agnostic and task- anddynamics-aware states. DAC-SSM jointly optimizes the state inference,observation reconstruction, forward dynamics, and reward models. To removedomain-dependent information from the states, the model is trained with domaindiscriminators in an adversarial manner, and the reconstruction is conditionedon domain labels. We experimentally evaluated the model predictive controlperformance via imitation learning for continuous control of sparse rewardtasks in simulators and compared it with the performance of the existing SRLmethod. The agents from DAC-SSM achieved performance comparable to experts andmore than twice the baselines. We conclude domain-agnostic states are essentialfor imitation learning that has large domain shifts and can be obtained usingDAC-SSM.

Domain-Adversarial and Conditional State Space Model for Imitation Learning