Zero-Shot Reward Specification via Grounded Natural Language
By Parsa Mahmoudieh, Deepak Pathak, Trevor Darrell. 2022
75 citations recorded by the source corpus.
Subfields: 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 Reinforcement Learning
- Sergey Levine
- Ofir Nachum
- Dale Schuurmans
- Mengjiao Yang
- Bo Dai
- Pieter Abbeel
- Chelsea Finn
- Josh Tenenbaum
Citations in the corpus
- Training Language Models with Language Feedback (2022, methodology): “Prior work uses language to specify the task (“instruction following” Chaplot et al., 2017; Mahmoudieh et al., 2022; Ouyang et al., 2022, inter alia ), drive exploration (Tam et al., 2022), infer reward functions (Lin et al., 2022; Sumers et al., 2021; Fidler et al., 2017, inter alia ), and train…”
- Foundation models in robotics: Applications, challenges, and the future (2023, unknown): “In [35], reward shaping using CLIP is presented.”
- Learning from Natural Language Feedback (2024, methodology): “This line of work generally focuses on using language to specify the task, as in instruction following (Chaplot et al., 2017; Mahmoudieh et al., 2022; Ouyang et al., 2022, inter alia ), rather than to correct a model’s behavior as in our work.”
- Learning Universal Policies via Text-Guided Video Generation (2023, background): “There has been a growing amount of work using text commands as a way to learn multi-task and generalist control policies (Huang et al., 2022; Ahn et al., 2022; Brohan et al., 2022; Lynch & Sermanet, 2020; Mahmoudieh et al., 2022; Liu et al., 2022).”
- Training Language Models with Natural Language Feedback (2022, methodology): “Prior work uses language to specify the task (“instruction following” Chaplot et al., 2017; Mahmoudieh et al., 2022; Ouyang et al., 2022, inter alia ), drive exploration (Tam et al., 2022), infer reward functions (Lin et al., 2022), and train the model via strong supervision (Andreas et al., 2017;…”
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities (2024, methodology): “These visually-grounded models have been used for several downstream tasks, such as in robotic success detection [18, 20, 54, 65], action prediction [7, 56], and reward prediction [16, 22, 46, 48].”