google-deepmind / simulation_streams
Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.
☆18Updated last month
Alternatives and similar repositories for simulation_streams:
Users that are interested in simulation_streams are comparing it to the libraries listed below
- SocialJax: sequential social dilemma environments☆26Updated last week
- A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.☆24Updated this week
- IIG-RL-Benchmark is a library for training and evaluating game theoretical or deep RL algorithms on OpenSpiel games.☆12Updated 2 months ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆9Updated last year
- A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers☆51Updated 2 years ago
- An Open-Ended Agentic Simulator☆47Updated 8 months ago
- Efficient baselines for autocurricula in JAX.☆187Updated 8 months ago
- ☆76Updated last month
- Exploitability calculation for imperfect-information game benchmarks☆24Updated 3 weeks ago
- Repo to reproduce the First-Explore paper results☆37Updated 4 months ago
- Learn online intrinsic rewards from LLM feedback☆35Updated 4 months ago
- Generative cellular automaton-like learning environments for RL.☆19Updated 2 months ago
- Learning diverse options through the Laplacian representation.☆23Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆46Updated 4 months ago
- A collection of matrix games in JAX☆10Updated 4 months ago
- Highly scalable 2D JAX physics engine.☆54Updated last month
- Drop-in environment replacements that make your RL algorithm train faster.☆20Updated 10 months ago
- ☆13Updated 9 months ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆14Updated last month
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated this week
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated 8 months ago
- ☆30Updated 2 months ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆89Updated 2 weeks ago
- Scalable Opponent Shaping Experiments in JAX☆24Updated last year
- ☆10Updated this week
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆27Updated 6 months ago
- Simple JAX Graphics Library.☆37Updated 5 months ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆17Updated 5 months ago
- Official implementation of the NeurIPS 2023 paper "Discovering General Reinforcement Learning Algorithms with Adversarial Environment Des…☆26Updated 9 months ago
- ☆72Updated last year