BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

By Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, Yoshua Bengio. 2018

188 citations recorded by the source corpus.

Subfields: Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

Experience Grounds Language (2020, background): “, 2006), a grid world (Chevalier-Boisvert et al., 2019), a simulated house (Anderson et al.”
Language Models as Knowledge Bases? (2019, background): “, 2019) or reinforcement learning (Branavan et al., 2011; Chevalier-Boisvert et al., 2018; Bahdanau et al., 2019; Luketina et al., 2019).”
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning (2020, methodology): “Embodied Language Learning : To address language learning in embodied domains, a number of interactive environments have been proposed: BabyAI (Chevalier-Boisvert et al., 2019), Room2Room (Anderson et al., 2018b), ALFRED (Shridhar et al., 2020), InteractiveQA (Gordon et al., 2018), EmbodiedQA (Das e”
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems (2020, methodology): “We use the GotoObjMaze environment (i.e MiniGrid-GotoObjMaze-v0) from [Chevalier-Boisvert et al., 2018].”
Recurrent Independent Mechanisms (2019, background): “These tasks are difficult to solve (Chevalier-Boisvert et al., 2018) with standard RL algorithms, due to (1) the partial observability of the environment and (2) the sparsity of the reward, given that the agent receives a reward only after reaching the goal.”
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text (2020, methodology): “Much recent work applies deep learning and policy optimization in end-to-end approaches to learning instruction following [Chaplot et al., 2018, Oh et al., 2017, Bahdanau et al., 2018, Chevalier-Boisvert et al., 2018, Yu et al., 2018b,a, Jiang et al., 2019].”
Inductive biases for deep learning of higher-level cognition (2020, background): “Studying this kind of setup was the motivation for our work on the Baby AI environment (Chevalier-Boisvert et al., 2018).”
Language as an Abstraction for Hierarchical Deep Reinforcement Learning (2019, background): “Lastly, there are a number of prior works that study how language can guide or improve reinforcement learning [27, 5, 19, 11, 9].”
Deep learning for AI (2021, background): “Current supervised learning systems require many more examples than humans (when having to learn a new task) and the situation is even worse for model-free reinforcement learning 23 since each re-warded trial provides less information about the task than each labeled example.”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, background): “Other work created a grid world evaluation domain with tasks of progressive difficulty (Chevalier-Boisvert et al., 2019).”
Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI (2022, background): “…autotelic agents can reach and make sense of abstract goals like “ go to any circle ,” 87 relational goals “ sort objects by size ,” 88 “ put the cylinder in the drawer ,” 89 sequential goals “ open the yellow door after opening a red door ,” 90 or even learning goals “ is the ghargh edible?”
HIGhER: Improving instruction following with Hindsight Generation for Experience Replay (2020, methodology): “We evaluate our method on the BabyAI world [12], showing a clear improvement over RL baselines while highlighting the robustness of HIGhER to noise.”
Continual Adaptation for Efficient Machine Communication (2019, background): “also related to broader efforts to ground language learning and emergent communication in usage, where artificial agents are trained to use language from scratch by playing interactive reference games (Wang et al., 2016; Lazaridou et al., 2016; Wang et al., 2017; Chevalier-Boisvert et al., 2019).”
Learning Rewards from Linguistic Feedback (2020, background): “…learning uses language to improve sample efﬁciency: to shape rewards (Maclin and Shavlik 1994; Kuhlmann et al. 2004), often via subgoals (Kaplan, Sauer, and Sosa 2017; Williams et al. 2018; Chevalier-Boisvert et al. 2018; Goyal, Niekum, and Mooney 2019; Bahdanau et al. 2019; Zhou and Small 2020).”
Learning to Generalize from Sparse and Underspecified Rewards (2019, background): “…environments where a learning agent is provided with a natural language input and asked to produce a sequence of actions for achieving a goal speciﬁed in the input text ( e.g., Long et al. (2016); Hermann et al. (2017); Chaplot et al. (2018); Fu et al. (2019); Chevalier-Boisvert et al. (2019)).”
Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention (2018, background): “Game-based and synthetic environments offer more complex visual contexts and interaction dynamics [33, 51, 9, 46, 22, 58, 14, 17].”
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning (2021, background): “…learning for robotics (Meta-World [Yu et al., 2019] and RLBench [James et al., 2020]) and for video gaming domain (Arcade Learning Environment, CoinRun [Cobbe et al., 2018], Sonic Benchmark [Machado et al., 2018], MazeBase [Nichol et al., 2018] and BabyAI [Chevalier-Boisvert et al., 2018]).”
Multi-Task Reinforcement Learning with Context-based Representations (2021, methodology): “These natural language descriptions have been utilized in single-task RL setups like goal-oriented RL (Chevalier-Boisvert et al., 2019; Luketina et al., 2019; Jiang et al., 2019).”