microsoft / NTTLinks
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation [ICML 2021]
☆14Updated last year
Alternatives and similar repositories for NTT
Users that are interested in NTT are comparing it to the libraries listed below
Sorting:
- Code that translates grammar into PDDL, runs a planner to produce multiple plans, translates plans into trainable lale pipelines and trai…☆18Updated last month
- Evaluating different engineering tricks that make RL work☆15Updated 4 years ago
- Game-based AI Platforms☆24Updated last year
- ☆14Updated last year
- Combining NEAT and novelty search to quickly generate diverse video game levels (GECCO 2022). https://arxiv.org/abs/2204.06934☆16Updated 2 years ago
- ☆10Updated 4 years ago
- Knowledge-Aware RL agents with Commonsense Reasoning☆79Updated 3 years ago
- ☆38Updated 10 months ago
- LLM Dynamic Planner - Combining LLM with PDDL Planners to solve an embodied task☆43Updated 5 months ago
- ☆22Updated 3 years ago
- This repository will contain code for the paper "CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot tr…☆24Updated last year
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆25Updated 4 years ago
- [ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games☆14Updated 3 years ago
- Codebase for "Causal Induction from Visual Observations for Goal-Directed Tasks"☆13Updated 5 years ago
- Minimal code for A Generalist Agent☆42Updated 2 years ago
- Repo to reproduce the First-Explore paper results☆37Updated 6 months ago
- Code accompanying "Learning What To Do by Simulating the Past", ICLR 2021.☆26Updated 4 years ago
- Code for the Ask4Help project☆22Updated 2 years ago
- Author implementation of Monte Carlo Augmented Actor Critic in PyTorch☆17Updated 2 years ago
- Code to reproduce Neural Game Engine experiments and pre-trained models☆41Updated 3 years ago
- Code for the paper Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration☆96Updated 2 years ago
- Code for the paper, "First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization"☆25Updated 2 years ago
- Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration☆32Updated 4 years ago
- ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS…☆20Updated 3 years ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆50Updated 5 months ago
- Research Into Learning to Generate Game Levels through Play☆30Updated 5 years ago
- Supplementary Data for Evolving Reinforcement Learning Algorithms☆46Updated 4 years ago
- Official codebase for Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings.☆21Updated 4 years ago
- Interactive GAN evolution of Mario and Zelda levels.☆54Updated last year
- Task planning over 3D scene graphs☆16Updated 2 years ago