Ai alignment: A comprehensive survey
AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …
Chatgpt for robotics: Design principles and model abilities
This paper presents an experimental study regarding the use of OpenAI's ChatGPT for
robotics applications. We outline a strategy that combines design principles for prompt …
robotics applications. We outline a strategy that combines design principles for prompt …
Open problems and fundamental limitations of reinforcement learning from human feedback
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …
to align with human goals. RLHF has emerged as the central method used to finetune state …
Language to rewards for robotic skill synthesis
Large language models (LLMs) have demonstrated exciting progress in acquiring diverse
new capabilities through in-context learning, ranging from logical reasoning to code-writing …
new capabilities through in-context learning, ranging from logical reasoning to code-writing …
Language models as zero-shot planners: Extracting actionable knowledge for embodied agents
Can world knowledge learned by large language models (LLMs) be used to act in
interactive environments? In this paper, we investigate the possibility of grounding high-level …
interactive environments? In this paper, we investigate the possibility of grounding high-level …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Vision-and-language navigation: A survey of tasks, methods, and future directions
A long-term goal of AI research is to build intelligent agents that can communicate with
humans in natural language, perceive the environment, and perform real-world tasks. Vision …
humans in natural language, perceive the environment, and perform real-world tasks. Vision …
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 …
Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments
We introduce BEHAVIOR, a benchmark for embodied AI with 100 activities in simulation,
spanning a range of everyday household chores such as cleaning, maintenance, and food …
spanning a range of everyday household chores such as cleaning, maintenance, and food …
Search on the replay buffer: Bridging planning and reinforcement learning
B Eysenbach, RR Salakhutdinov… - Advances in neural …, 2019 - proceedings.neurips.cc
The history of learning for control has been an exciting back and forth between two broad
classes of algorithms: planning and reinforcement learning. Planning algorithms effectively …
classes of algorithms: planning and reinforcement learning. Planning algorithms effectively …