BabyAI 1.1
Not on the map. Why?
Abstract (arXiv)
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 0; 2025: 3.
8 papers.
- 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 35
- 2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinkingcited by 30
- 2021A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learningcited by 27
- 2022Combining Modular Skills in Multitask Learningcited by 27
- 2023Active Reward Learning from Online Preferencescited by 12
- 2025Model-Agnostic Policy Explanations with Large Language Modelscited by 4
- 2025DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learningcited by 1
- 2025Data Augmentation for Instruction Following Policies via Trajectory Segmentationcited by 0
- 2025DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning22 Oct 2025
- 2025Model-Agnostic Policy Explanations with Large Language Models8 Apr 2025
- 2025Data Augmentation for Instruction Following Policies via Trajectory Segmentation25 Feb 2025
- 2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinking1 Jun 2023
- 2023Active Reward Learning from Online Preferences27 Feb 2023
- 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectory29 Dec 2022
- 2022Combining Modular Skills in Multitask Learning28 Feb 2022
- 2021A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning3 Jun 2021
Similar, not cited
Close in wording, no citation either way
- 2023Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning
- 2020Combating False Negatives in Adversarial Imitation Learning
- 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
- 2020BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
- 2024MaIL: Improving Imitation Learning with Mamba
- 2022Planning for Sample Efficient Imitation Learning
- 2022Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
- 2023Scaling Laws for Imitation Learning in Single-Agent Games