Solving Safety Problems with Ensemble Reinforcement Learning

Ferreira, Leonardo Anjoletto; Santos, Thiago Freitas dos; Bianchi, Reinaldo A. C.; Santos, Paulo E.

doi:10.1007/978-3-030-35288-2_17

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those algorithms exploited the flexibility of RL approaches and the accuracy of the declarative knowledge from humans. Other algorithms use action knowledge to improve model-free RL agents' performance in exploratory behaviors (Ferreira et al 2019;Zhang et al 2019). In these works, researchers exploited the pre-designed models for constraining the state or action spaces.…”

Section: Related Workmentioning

confidence: 99%

Guiding Robot Exploration in Reinforcement Learning via Automated Planning

Hayamizu

Amiri

Chandan

et al. 2021

ICAPS

View full text Add to dashboard Cite

Reinforcement learning (RL) enables an agent to learn from trial-and-error experiences toward achieving long-term goals; automated planning aims to compute plans for accomplishing tasks using action knowledge. Despite their shared goal of completing complex tasks, the development of RL and automated planning has been largely isolated due to their different computational modalities. Focusing on improving RL agents' learning efficiency, we develop Guided Dyna-Q (GDQ) to enable RL agents to reason with action knowledge to avoid exploring less-relevant states. The action knowledge is used for generating artificial experiences from an optimistic simulation. GDQ has been evaluated in simulation and using a mobile robot conducting navigation tasks in a multi-room office environment. Compared with competitive baselines, GDQ significantly reduces the effort in exploration while improving the quality of learned policies.

show abstract

Section: Related Workmentioning

confidence: 99%