9

Redistribution-based Cost Inference Improves Sparse Safe Offline RL
Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level …
PDF Cite
The Goal-Directed Frame for General Agents
Reinforcement learning is often framed around episodic, discounted, or average scalar rewards. While useful, these views miss a core …
PDF Cite
CORDA: A Benchmark for Hierarchical Harm-Centric Moral Reasoning in Large Language Models
The key question in moral judgement is not simply whether someone chooses the “right” answer, but how they decide what …
PDF Cite
AI Agent Safety is a Reinforcement Learning Problem
With the rapid advancement and deployment of Agentic AI, our scientific understanding of capabilities and limitations has not kept …
PDF Cite
Schema-Based Understandability in Human-Robot Interactions: A Cognitive Framework
Robots are entering hospitals, airports, classrooms and homes, yet a persistent barrier to effective human–robot interaction is often …
PDF Cite
The Five Senses: Assessing Non-verbal Communication in Multicultural Human–Robot Interaction
As social robots move from research laboratories into everyday settings, they increasingly encounter users whose sensory expectations …
PDF Cite
Finding the FrameStack: Learning What to Remember for Non-Markovian Reinforcement Learning
Recent success in developing increasingly general purpose agents based on sequence models has led to increased focus on the problem of …
PDF Cite
Procedural Generation of Semantically Correct Levels in Video Games using Reward Shaping
The generation of video game levels traditionally relies on manual efforts from skilled professionals, resulting in significant …
PDF Cite Project
A Linear Network Theory of Iterated Learning
Language provides one of the primary examples of human’s ability to systematically generalize — reasoning about new …
PDF Cite
Optimal Task Generalisation in Cooperative Multi-Agent Reinforcement Learning
While task generalisation is widely studied in the context of single-agent reinforcement learning (RL), little research exists in the …
PDF Cite Project