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/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

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

Zendy Tools

Zendy Open

Deep reinforcement learning has led to several recent breakthroughs, thoughthe learned policies are often based on black-box neural networks. This makesthem difficult to interpret and to impose desired specification constraintsduring learning. We present an iterative framework, MORL, for improving thelearned policies using program synthesis. Concretely, we propose to usesynthesis techniques to obtain a symbolic representation of the learned policy,which can then be debugged manually or automatically using program repair.After the repair step, we use behavior cloning to obtain the policycorresponding to the repaired program, which is then further improved usinggradient descent. This process continues until the learned policy satisfiesdesired constraints. We instantiate MORL for the simple CartPole problem andshow that the programmatic representation allows for high-level modificationsthat in turn lead to improved learning of the policies.

Towards Mixed Optimization for Reinforcement Learning with Program Synthesis