# BabyAI 1.1

arXiv: https://arxiv.org/abs/2007.12770 · HTML: https://mlsanity.com/paper/2007.12770/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [On Transforming Reinforcement Learning by Transformer: The Development Trajectory](https://mlsanity.com/paper/2212.14164/) (2022)
- [Thought Cloning: Learning to Think while Acting by Imitating Human Thinking](https://mlsanity.com/paper/2306.00323/) (2023)
- [Combining Modular Skills in Multitask Learning](https://mlsanity.com/paper/2202.13914/) (2022)
- [A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2106.02097/) (2021)
- [Active Reward Learning from Online Preferences](https://mlsanity.com/paper/2302.13507/) (2023)
- [Model-Agnostic Policy Explanations with Large Language Models](https://mlsanity.com/paper/2504.05625/) (2025)
- [DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2510.19562/) (2025)
- [Data Augmentation for Instruction Following Policies via Trajectory Segmentation](https://mlsanity.com/paper/2503.01871/) (2025)

## 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.