google-deepmind / simulation_streamsLinks
Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.
☆23Updated 5 months ago
Alternatives and similar repositories for simulation_streams
Users that are interested in simulation_streams are comparing it to the libraries listed below
Sorting:
- Efficient baselines for autocurricula in JAX.☆194Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆65Updated 7 months ago
- An Open-Ended Agentic Simulator☆52Updated last year
- Repo to reproduce the First-Explore paper results☆38Updated 8 months ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆29Updated last month
- Exploitability calculation for imperfect-information game benchmarks☆29Updated 4 months ago
- Drop-in environment replacements that make your RL algorithm train faster.☆21Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- Interpreting how transformers simulate agents performing RL tasks☆87Updated last year
- Formal Contracts for Multi-Agent Reinforcement Learning☆19Updated last year
- ☆82Updated 5 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆63Updated 6 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆73Updated last year
- IIG-RL-Benchmark is a library for training and evaluating game theoretical or deep RL algorithms on OpenSpiel games.☆18Updated last month
- ☆13Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆105Updated 11 months ago
- ☆12Updated 2 months ago
- ☆43Updated last month
- Simple JAX Graphics Library.☆36Updated 9 months ago
- Learn online intrinsic rewards from LLM feedback☆43Updated 8 months ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆11Updated 2 years ago
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆202Updated last month
- ☆70Updated 3 years ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆54Updated 6 months ago
- Code for Powderworld: A Platform for Understanding Generalization via Rich Task Distributions☆68Updated 11 months ago
- A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.☆81Updated this week
- ☆75Updated last year
- A collection of matrix games in JAX☆11Updated 8 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆93Updated 5 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆180Updated 5 months ago