Safety

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 …
Ebenezer Gelo, Geraud Nangue Tasse, Steven James, Benjamin Rosman
PDF Cite
An Unreasonably Simple Approach to Safe RL
An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common …
Geraud Nangue Tasse, Mark Nemecek, Tamlin Love, Steven James, Benjamin Rosman
PDF Cite Code
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 …
Siddarth Singh, Victoria Williams, Simon Rosen, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Benjamin Rosman, Geraud Nangue Tasse, Steven James
PDF Cite
MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents
Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the …
Simon Rosen, Siddarth Singh, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Victoria Williams, Benjamin Rosman, Geraud Nangue Tasse, Steven James
PDF Cite
ROSARL: Reward-Only Safe Reinforcement Learning
An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common …
Geraud Nangue Tasse, Tamlin Love, Mark Nemecek, Steven James, Benjamin Rosman
PDF Cite