minerllabs / basalt-benchmarkLinks
BASALT Benchmark datasets, evaluation code and agent training example.
☆21Updated last year
Alternatives and similar repositories for basalt-benchmark
Users that are interested in basalt-benchmark are comparing it to the libraries listed below
Sorting:
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆113Updated last year
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆46Updated 2 years ago
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆84Updated 9 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94Updated 2 years ago
- Code for Contrastive Preference Learning (CPL)☆176Updated 11 months ago
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (ICLR 2024 Spotlight)☆66Updated last year
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆57Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆76Updated last year
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆28Updated last year
- ☆15Updated last year
- Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)☆33Updated 2 years ago
- Code for Powderworld: A Platform for Understanding Generalization via Rich Task Distributions☆69Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆142Updated last year
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆34Updated 3 months ago
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆129Updated last year
- Learning diverse options through the Laplacian representation.☆23Updated last year
- Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]☆130Updated 3 years ago
- Text world based on Minecraft rules.☆16Updated last year
- MTM Masked Trajectory Models for Prediction, Representation, and Control.☆158Updated 2 years ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆135Updated last year
- VC-FB and MC-FB algorithms from "Zero-Shot Reinforcement Learning from Low Quality Data" (NeurIPS 2024)☆20Updated 9 months ago
- STEVE-1: A Generative Model for Text-to-Behavior in Minecraft☆194Updated last year
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆55Updated 10 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning…☆69Updated 2 years ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆46Updated last year
- Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"☆135Updated 2 years ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆78Updated 2 years ago
- Object Centric Atari games☆93Updated this week
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year