ygjin11 / r2-play
The official implementation of the paper "Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction".
☆34Updated last year
Alternatives and similar repositories for r2-play:
Users that are interested in r2-play are comparing it to the libraries listed below
- [ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control☆54Updated 2 months ago
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆41Updated 9 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos☆64Updated last year
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆66Updated last year
- ☆44Updated last year
- ☆52Updated 2 weeks ago
- Code for "Interactive Task Planning with Language Models"☆27Updated last year
- MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft☆16Updated last year
- ☆82Updated 9 months ago
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆135Updated 11 months ago
- ☆27Updated this week
- The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Pla…☆85Updated 7 months ago
- ☆103Updated 2 months ago
- Natural Language Reinforcement Learning☆80Updated 3 months ago
- Official Repo of LangSuitE☆83Updated 7 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆46Updated last year
- LLM Dynamic Planner - Combining LLM with PDDL Planners to solve an embodied task☆41Updated 2 months ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆130Updated 3 months ago
- ☆82Updated 8 months ago
- NeurIPS 2024 tutorial on LLM Inference☆39Updated 3 months ago
- ☆24Updated 6 months ago
- A testbed for agents and environments that can automatically improve models through data generation.☆21Updated 2 weeks ago
- ☆25Updated 11 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆86Updated 5 months ago
- ☆81Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆54Updated 3 weeks ago
- ☆37Updated 3 weeks ago
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆27Updated 5 months ago