Semantic memory: A review of methods, models, and current challenges
AA Kumar - Psychonomic Bulletin & Review, 2021 - Springer
Adult semantic memory has been traditionally conceptualized as a relatively static memory
system that consists of knowledge about the world, concepts, and symbols. Considerable …
system that consists of knowledge about the world, concepts, and symbols. Considerable …
Deep reinforcement learning: An overview
Y Li - arXiv preprint arXiv:1701.07274, 2017 - arxiv.org
We give an overview of recent exciting achievements of deep reinforcement learning (RL).
We discuss six core elements, six important mechanisms, and twelve applications. We start …
We discuss six core elements, six important mechanisms, and twelve applications. We start …
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …
capabilities with increasing scale. Despite their potentially transformative impact, these new …
Do as i can, not as i say: Grounding language in robotic affordances
M Ahn, A Brohan, N Brown, Y Chebotar… - arXiv preprint arXiv …, 2022 - arxiv.org
Large language models can encode a wealth of semantic knowledge about the world. Such
knowledge could be extremely useful to robots aiming to act upon high-level, temporally …
knowledge could be extremely useful to robots aiming to act upon high-level, temporally …
Coauthor: Designing a human-ai collaborative writing dataset for exploring language model capabilities
Large language models (LMs) offer unprecedented language generation capabilities and
exciting opportunities for interaction design. However, their highly context-dependent …
exciting opportunities for interaction design. However, their highly context-dependent …
Cognitive architectures for language agents
Recent efforts have incorporated large language models (LLMs) with external resources (eg,
the Internet) or internal control flows (eg, prompt chaining) for tasks requiring grounding or …
the Internet) or internal control flows (eg, prompt chaining) for tasks requiring grounding or …
Deep reinforcement learning from human preferences
For sophisticated reinforcement learning (RL) systems to interact usefully with real-world
environments, we need to communicate complex goals to these systems. In this work, we …
environments, we need to communicate complex goals to these systems. In this work, we …
Learning language-conditioned robot behavior from offline data and crowd-sourced annotation
We study the problem of learning a range of vision-based manipulation tasks from a large
offline dataset of robot interaction. In order to accomplish this, humans need easy and …
offline dataset of robot interaction. In order to accomplish this, humans need easy and …
Embodied question answering
We present a new AI task--Embodied Question Answering (EmbodiedQA)--where an agent
is spawned at a random location in a 3D environment and asked a question (" What color is …
is spawned at a random location in a 3D environment and asked a question (" What color is …
Memory-assisted prompt editing to improve GPT-3 after deployment
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to
humans. For example, GPT-3 would mistakenly interpret" What word is similar to good?" to …
humans. For example, GPT-3 would mistakenly interpret" What word is similar to good?" to …