Grounding Language to Autonomously-Acquired Skills via Goal Generation

By Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud. 2021

73 citations recorded by the source corpus.

Subfields: LLM Agents & Tool Use, 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 LLM Agents & Tool Use

1. Andy Zeng
2. Dieter Fox
3. Brian Ichter
4. Chelsea Finn
5. Fei Xia
6. Suraj Nair
7. Sergey Levine
8. Ishika Singh

In Reinforcement Learning

1. Sergey Levine
2. Chelsea Finn
3. Pieter Abbeel
4. Karol Hausman
5. Dieter Fox
6. Silvio Savarese
7. Pierre Sermanet
8. Suraj Nair

Citations in the corpus

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022, methodology): “A large number of prior works have learned language-conditioned behavior via imitation learning [51, 22, 20, 13, 26, 37] or reinforcement learning [52, 53, 49, 54, 55, 56, 21, 41].”
• Inner Monologue: Embodied Reasoning through Planning with Language Models (2022, background): “Traditionally, this problem has been solved through optimization [28, 29] or symbolic reasoning [24, 26], but more recently machine learning has been applied to aspects of the problem via learned representations, learned task-primitives, and more [30, 31, 32, 33, 34, 35, 36, 37, 38].”
• Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation (2021, background): “More recently, end-to-end deep learning has been used to condition agents on natural language instructions [37, 24, 38, 27, 39, 6, 7, 40], which are then trained under an imitation and/or reinforcement learning objective.”
• Code as Policies: Language Model Programs for Embodied Control (2022, unknown): “, model-based [33]–[35], imitation learning [8], [9], [36], [37], or reinforcement learning [38]–[42]).”
• ProgPrompt: Generating Situated Robot Task Plans using Large Language Models (2022, background): “Recent works have explored learning-based task & motion planning, using methods such as representation learning, hierarchical learning, language as planning space, learning compositional skills and more [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], [25], [26].”