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

This paper focuses on inverse reinforcement learning (IRL) to enable safe andefficient autonomous navigation in unknown partially observable environments.The objective is to infer a cost function that explains expert-demonstratednavigation behavior while relying only on the observations and state-controltrajectory used by the expert. We develop a cost function representationcomposed of two parts: a probabilistic occupancy encoder, with recurrentdependence on the observation sequence, and a cost encoder, defined over theoccupancy features. The representation parameters are optimized bydifferentiating the error between demonstrated controls and a control policycomputed from the cost encoder. Such differentiation is typically computed bydynamic programming through the value function over the whole state space. Weobserve that this is inefficient in large partially observable environmentsbecause most states are unexplored. Instead, we rely on a closed-formsubgradient of the cost-to-go obtained only over a subset of promising statesvia an efficient motion-planning algorithm such as A* or RRT. Our experimentsshow that our model exceeds the accuracy of baseline IRL algorithms in robotnavigation tasks, while substantially improving the efficiency of training andtest-time inference.

Learning Navigation Costs from Demonstration in Partially Observable Environments