Biological and Economical Alignment Benchmarks
Popular repositories Loading
-
ai-safety-gridworlds
ai-safety-gridworlds PublicForked from google-deepmind/ai-safety-gridworlds
Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environmen…
-
biological-alignment-gridagents-benchmarks
biological-alignment-gridagents-benchmarks PublicSafety challenges for RL and LLM agents' ability to learn and use biologically and economically aligned utility functions. The benchmarks are implemented in a gridworld-based environment. The envir…
-
zoo_to_gym_multiagent_adapter
zoo_to_gym_multiagent_adapter PublicEnables you to convert a PettingZoo environment to a Gym environment while supporting multiple agents (MARL). Gym's default setup doesn't easily support multi-agent environments, but this wrapper r…
Python 2
Repositories
- biological-alignment-gridagents-benchmarks Public
Safety challenges for RL and LLM agents' ability to learn and use biologically and economically aligned utility functions. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.
biological-alignment-benchmarks/biological-alignment-gridagents-benchmarks’s past year of commit activity - ai-safety-gridworlds Public Forked from google-deepmind/ai-safety-gridworlds
Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.
biological-alignment-benchmarks/ai-safety-gridworlds’s past year of commit activity - zoo_to_gym_multiagent_adapter Public
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-agent environments, but this wrapper resolves that by running each agent in its own process and sharing the environment across those processes.
biological-alignment-benchmarks/zoo_to_gym_multiagent_adapter’s past year of commit activity - bioblue Public
Systematic runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLM-s with simplified observation format. The benchmark themes include multi-objective homeostasis, (multi-objective) diminishing returns, complementary goods, sustainability, multi-agent resource sharing.
biological-alignment-benchmarks/bioblue’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…