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 …
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 …
No, to the right: Online language corrections for robotic manipulation via shared autonomy
Systems for language-guided human-robot interaction must satisfy two key desiderata for
broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction …
broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction …
A survey on autonomous vehicle control in the era of mixed-autonomy: From physics-based to AI-guided driving policy learning
This paper serves as an introduction and overview of the potentially useful models and
methodologies from artificial intelligence (AI) into the field of transportation engineering for …
methodologies from artificial intelligence (AI) into the field of transportation engineering for …
Interactive imitation learning in robotics: A survey
Interactive Imitation Learning in Robotics: A Survey Page 1 Interactive Imitation Learning in
Robotics: A Survey Page 2 Other titles in Foundations and Trends® in Robotics A Survey on …
Robotics: A Survey Page 2 Other titles in Foundations and Trends® in Robotics A Survey on …
A survey of reinforcement learning from human feedback
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning
(RL) that learns from human feedback instead of relying on an engineered reward function …
(RL) that learns from human feedback instead of relying on an engineered reward function …
Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning
Abstract Setting up a well-designed reward function has been challenging for many
reinforcement learning applications. Preference-based reinforcement learning (PbRL) …
reinforcement learning applications. Preference-based reinforcement learning (PbRL) …
B-pref: Benchmarking preference-based reinforcement learning
Reinforcement learning (RL) requires access to a reward function that incentivizes the right
behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL …
behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL …
Recent advances in leveraging human guidance for sequential decision-making tasks
A longstanding goal of artificial intelligence is to create artificial agents capable of learning
to perform tasks that require sequential decision making. Importantly, while it is the artificial …
to perform tasks that require sequential decision making. Importantly, while it is the artificial …
SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning
Preference-based reinforcement learning (RL) has shown potential for teaching agents to
perform the target tasks without a costly, pre-defined reward function by learning the reward …
perform the target tasks without a costly, pre-defined reward function by learning the reward …