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

In safety-critical robotic tasks, potential failures must be reduced, andmultiple constraints must be met, such as avoiding collisions, limiting energyconsumption, and maintaining balance. Thus, applying safe reinforcementlearning (RL) in such robotic tasks requires to handle multiple constraints anduse risk-averse constraints rather than risk-neutral constraints. To this end,we propose a trust region-based safe RL algorithm for multiple constraintscalled a safe distributional actor-critic (SDAC). Our main contributions are asfollows: 1) introducing a gradient integration method to manage infeasibilityissues in multi-constrained problems, ensuring theoretical convergence, and 2)developing a TD($\lambda$) target distribution to estimate risk-averseconstraints with low biases. We evaluate SDAC through extensive experimentsinvolving multi- and single-constrained robotic tasks. While maintaining highscores, SDAC shows 1.93 times fewer steps to satisfy all constraints inmulti-constrained tasks and 1.78 times fewer constraint violations insingle-constrained tasks compared to safe RL baselines. Code is available at:https://github.com/rllab-snu/Safe-Distributional-Actor-Critic.

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints