stanfordnlp / wge
Workflow-Guided Exploration: sample-efficient RL agent for web tasks
☆113Updated last year
Alternatives and similar repositories for wge:
Users that are interested in wge are comparing it to the libraries listed below
- MiniWoB++: a web interaction benchmark for reinforcement learning☆313Updated last year
- Graph-based Deep Q Network for Web Navigation☆47Updated 5 years ago
- Demos for the MiniWoB++ benchmark☆19Updated 7 years ago
- We release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce…☆162Updated 3 years ago
- CLEVR-Robot: a reinforcement learning environment combining vision, language and control.☆133Updated 8 months ago
- Template-DQN and DRRN agent implementations☆22Updated last year
- Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".☆38Updated 3 years ago
- Code for Emergent Translation in Multi-Agent Communication☆80Updated 6 years ago
- Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.☆79Updated last year
- An implementation of Emergence of Grounded Compositional Language in Multi-Agent Populations by Igor Mordatch and Pieter Abbeel☆72Updated 7 years ago
- Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"☆197Updated 6 years ago
- [ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement☆123Updated 5 years ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆226Updated 5 months ago
- Code for "Learning Compositional Rules via Neural Program Synthesis"☆60Updated 4 years ago
- impact-driven-exploration☆130Updated last year
- ☆20Updated 3 years ago
- Python and TensorFlow implementation of the paper "Learning Explanatory Rules from Noisy Data." Evans Richard and Edward Grefenstette. Jo…☆51Updated 3 years ago
- ☆84Updated 5 years ago
- [NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"☆116Updated 5 years ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆254Updated 7 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆253Updated 6 months ago
- ☆39Updated 7 months ago
- Neural Programmer-Interpreter Implementation (Reed, de Freitas: https://arxiv.org/abs/1511.06279), in Tensorflow☆41Updated 6 years ago
- NLPGym - A toolkit to develop RL agents to solve NLP tasks.☆199Updated 2 years ago
- Automatically Composing Representation Transformations as a Means for Generalization☆24Updated 5 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…☆67Updated last year
- Soft Actor-Critic☆144Updated 7 years ago
- Grounded SCAN data set.☆69Updated 3 years ago
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆70Updated last year
- ☆16Updated 4 years ago