Learning to Parse Natural Language to Grounded Reward Functions with Weak Supervision

By Edward C. Williams, Nakul Gopalan, Mina Rhee, Stefanie Tellex. 2018

61 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

Learning to Understand Goal Specifications by Modelling Reward (2018, methodology): “There have been earlier attempts to use IRL-style methods for instruction following (MacGlashan et al., 2015; Williams et al., 2018), but unlike AGILE, they relied on the availability of a formal reward speciﬁcation language.”
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning (2018, background): “…research on instruction following with natural language (Tellex et al., 2011; Chen and Mooney, 2011; Artzi and Zettlemoyer, 2013; Mei et al., 2016; Williams et al., 2018) as well as several datasets including SAIL (Macmahon et al., 2006; Chen and Mooney, 2011) and Room-to-Room (Anderson et al.,…”
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning (2018, background): “The approach of Williams et al. (2017) learns a natural language parser from single goal instructions to a sparse reward function.”
Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following (2020, background): “Natural language instruction following on physical robots is most commonly studied using handengineered symbolic representations of world state or instruction semantics [1, 7, 2, 3, 4, 8, 5, 9], which require representation design and state estimation pipelines that are hard to scale to complex envi”
BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop (2018, background): “There has been much research on instruction following with natural language (Tellex et al., 2011; Chen and Mooney, 2011; Artzi and Zettlemoyer, 2013; Mei et al., 2016; Williams et al., 2018) and several datasets, such as e.”
Correcting Robot Plans with Natural Language Feedback (2022, background): “2) Language for Robot Task Speciﬁcation: Natural language has been extensively studied as a means for task speci-ﬁcation or instruction following in robotics [37, 22, 15, 4, 28, 43, 8, 31].”
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight (2019, background): “Natural language instruction following has been extensively studied using hand-engineered symbolic intermediate representations of world state or instruction semantics with physical robots [1, 2, 3, 4, 17, 5, 18, 6, 19] and simulated agents [20, 21, 22, 23, 24, 25].”
Using Natural Language for Reward Shaping in Reinforcement Learning (2019, background): “[Williams et al. , 2017] and [Arumugam et al. , 2017] map language to a reward function in an object-oriented MDP framework.”
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (2019, background): “…Shah et al., 2018), simulations of realistic (Blukis et al., 2018; Misra et al., 2018) and real environments (Anderson et al., 2018b; de Vries et al., 2018; Chen et al., 2019; Cirik et al., 2018), or actual physical environments (Skočaj et al., 2016; Thomason et al., 2018; Williams et al., 2018).”
PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards (2020, background): “However, these techniques are still quite restrictive, often requiring object properties to be predefined (MacGlashan et al., 2014; Williams et al., 2017) and/or assuming some structure in the natural language commands (Bahdanau et al.”
Multi-Task Reinforcement Learning with Context-based Representations (2021, background): “, 2017), and instruction following (Tellex et al., 2011; Chen & Mooney, 2011; Williams et al., 2018).”
Effective and General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping (2019, background): “These can be both virtual—sometimes photo-realistic—[1, 2, 3, 4, 5] or physical environments [6, 7, 8].”