understanding-search / maze-transformerLinks
This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
☆31Updated last year
Alternatives and similar repositories for maze-transformer
Users that are interested in maze-transformer are comparing it to the libraries listed below
Sorting:
- Interpreting how transformers simulate agents performing RL tasks☆88Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆98Updated last week
- ☆39Updated last month
- An Open-Ended Agentic Simulator☆52Updated last year
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆110Updated last year
- see github.com/understanding-search/maze-transformer☆10Updated last year
- Scaling scaling laws with board games.☆53Updated 2 years ago
- ☆52Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆27Updated last year
- Scalable Opponent Shaping Experiments in JAX☆24Updated last year
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆12Updated 2 years ago
- ☆13Updated last year
- Official codebase for "Sampling For Learnability", published at NeurIPS 2024☆18Updated 4 months ago
- Official Implementation of `An Optimisation Framework for Unsupervised Environment Design` from RLC 2025☆15Updated last month
- Comparison between GFlowNets & Maximum Entropy RL☆19Updated last year
- POPGym Library in JAX☆11Updated last year
- TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.☆21Updated 2 weeks ago
- ☆55Updated 11 months ago
- ☆73Updated last year
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆17Updated 2 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated last year
- Code for Powderworld: A Platform for Understanding Generalization via Rich Task Distributions☆68Updated last year
- maze datasets for investigating OOD behavior of ML systems☆54Updated last month
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆28Updated last year
- ICML 2022: Learning Iterative Reasoning through Energy Minimization☆48Updated 2 years ago
- Standardized Minecraft Diamond Environment for Reinforcement Learning☆31Updated 2 years ago
- ☆84Updated last month
- Building blocks for productive research☆62Updated 2 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆108Updated last year