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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The application of reinforcement learning (RL) in robotic control is stilllimited in the environments with sparse and delayed rewards. In this paper, wepropose a practical self-imitation learning method named Self-ImitationLearning with Constant Reward (SILCR). Instead of requiring hand-definedimmediate rewards from environments, our method assigns the immediate rewardsat each timestep with constant values according to their final episodicrewards. In this way, even if the dense rewards from environments areunavailable, every action taken by the agents would be guided properly. Wedemonstrate the effectiveness of our method in some challenging continuousrobotics control tasks in MuJoCo simulation and the results show that ourmethod significantly outperforms the alternative methods in tasks with sparseand delayed rewards. Even compared with alternatives with dense rewardsavailable, our method achieves competitive performance. The ablationexperiments also show the stability and reproducibility of our method.

Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards