53 citations · 87 across the 25 of their papers we have counts for
5 papers · 1 filter
Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing
Thien Q. Tran, Akifumi Wachi, Rei Sato +2
Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment method…
LOA: Logical Optimal Actions for Text-based Interaction Games
Daiki Kimura, Subhajit Chaudhury, Masaki Ono +6
We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural ne…
Neuro-Symbolic Reinforcement Learning with First-Order Logic
Daiki Kimura, Masaki Ono, Subhajit Chaudhury +6
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast conv…
Reinforcement Learning with External Knowledge by using Logical Neural Networks
Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi +4
Conventional deep reinforcement learning methods are sample-inefficient and usually require a large number of training trials before convergence. Since such methods operate on an u…
Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process
Akifumi Wachi, Hiroshi Kajino, Asim Munawar
In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration a…