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.
☆22Updated 7 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:
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆69Updated 10 months ago
- Efficient baselines for autocurricula in JAX.☆199Updated last year
- Repo to reproduce the First-Explore paper results☆38Updated 10 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated 2 years ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆57Updated 9 months ago
- An Open-Ended Agentic Simulator☆52Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆65Updated 8 months ago
- ☆14Updated last year
- Drop-in environment replacements that make your RL algorithm train faster.☆21Updated last year
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆36Updated 3 months ago
- A collection of matrix games in JAX☆12Updated 11 months ago
- ☆86Updated last month
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆12Updated 2 years ago
- Exploitability calculation for imperfect-information game benchmarks☆32Updated 7 months ago
- Learn online intrinsic rewards from LLM feedback☆44Updated 10 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆113Updated last year
- A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers☆55Updated 2 years ago
- Formal Contracts for Multi-Agent Reinforcement Learning☆19Updated 2 years ago
- A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.☆126Updated this week
- Learning diverse options through the Laplacian representation.☆23Updated last year
- ☆73Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated last year
- General multi-task deep RL Agent☆185Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆117Updated 4 months ago
- Interpreting how transformers simulate agents performing RL tasks☆88Updated 2 years ago
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆71Updated 2 years ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆188Updated 7 months ago
- Awesome Open-ended AI☆359Updated 3 weeks ago
- Unified Implementations of Offline Reinforcement Learning Algorithms☆117Updated 3 weeks ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆117Updated last year