Biological and Economical Alignment Benchmarks
Change the repository type filter
All
Repositories list
4 repositories
- Safety challenges for RL and LLM agents' ability to learn and use biologically and economically aligned utility functions. The benchmarks are implemented in a g…
ai-safety-gridworlds
PublicExtended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite…- Enables you to convert a PettingZoo environment to a Gym environment while supporting multiple agents (MARL). Gym's default setup doesn't easily support multi-a…
bioblue
PublicSystematic runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLM-s with simplified observation format. …