Interpreting how transformers simulate agents performing RL tasks
☆90Oct 23, 2023Updated 2 years ago
Alternatives and similar repositories for DecisionTransformerInterpretability
Users that are interested in DecisionTransformerInterpretability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Research project for Deep Reinforcement Learning using Decision Transformer☆16May 12, 2023Updated 3 years ago
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 4 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated 8 months ago
- ☆20Feb 17, 2023Updated 3 years ago
- ☆15Jul 12, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A spruced up version of the built-in python list. More post fixed methods for lovely typesafe chaining!☆13Nov 24, 2025Updated 7 months ago
- Implementation of Multi-Game Decision Transformers in PyTorch☆49Feb 11, 2023Updated 3 years ago
- Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in Open…☆294Jun 10, 2022Updated 4 years ago
- Generative cellular automaton-like learning environments for RL.☆20Jan 30, 2025Updated last year
- ☆219Oct 14, 2025Updated 8 months ago
- TransformerLens + HuggingFace☆11Nov 4, 2023Updated 2 years ago
- ☆29Apr 30, 2024Updated 2 years ago
- A library for mechanistic interpretability of GPT-style language models☆3,603Jun 27, 2026Updated last week
- Mechanistic Interpretability Visualizations using React☆353Apr 30, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Fluent dreaming for language models☆13Jul 22, 2024Updated last year
- Counterfactual explanations for Reinforcement Learning agents on Atari☆12Apr 3, 2023Updated 3 years ago
- 🔥 [ICLR 2026] Official implementation of Recurrent Action Transformer with Memory, an offline RL agent with memory mechanisms. https://s…☆28Nov 23, 2025Updated 7 months ago
- Decoder only transformer, built from scratch with PyTorch☆33Oct 22, 2023Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,442Jun 24, 2026Updated last week
- A formalisation of Cartesian Frames, a perspective on embedded agency, in the HOL theorem prover.☆22Dec 20, 2021Updated 4 years ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆24Oct 28, 2024Updated last year
- ☆60Apr 22, 2024Updated 2 years ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆57Oct 23, 2023Updated 2 years ago
- A web based platform for collecting human actions in reinforcement learning environments☆31Sep 10, 2025Updated 9 months ago
- ☆174May 1, 2026Updated 2 months ago
- ☆30Jun 19, 2023Updated 3 years ago
- Retrieval-Augmented Decision Transformer: External Memory for In-context RL☆26Oct 27, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆888Mar 6, 2026Updated 3 months ago
- Official code repository for Prompt-DT.☆123Aug 3, 2022Updated 3 years ago
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- Benchmarking of Neural Network Architectures in Reinforcement Learning.☆39Jan 22, 2026Updated 5 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆206Updated this week
- [NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning☆35Feb 22, 2021Updated 5 years ago
- Tools for studying developmental interpretability in neural networks.☆140Apr 23, 2026Updated 2 months ago
- Implementation of ICML 2023 paper: Future-conditioned Unsupervised Pretraining for Decision Transformer☆29Jul 25, 2023Updated 2 years ago
- ☆30Aug 20, 2021Updated 4 years ago
- ☆10Oct 9, 2022Updated 3 years ago
- Decision Transformer for offline single-agent autonomous highway driving☆29Jun 19, 2023Updated 3 years ago