Safe learning in robotics: From learning-based control to safe reinforcement learning
The last half decade has seen a steep rise in the number of contributions on safe learning
methods for real-world robotic deployments from both the control and reinforcement learning …
methods for real-world robotic deployments from both the control and reinforcement learning …
A survey on offline reinforcement learning: Taxonomy, review, and open problems
RF Prudencio, MROA Maximo… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …
experienced a dramatic increase in popularity, scaling to previously intractable problems …
Planning with diffusion for flexible behavior synthesis
Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …
estimating an approximate dynamics model, offloading the rest of the decision-making work …
Pretraining language models with human preferences
Abstract Language models (LMs) are pretrained to imitate text from large and diverse
datasets that contain content that would violate human preferences if generated by an LM …
datasets that contain content that would violate human preferences if generated by an LM …
Multi-game decision transformers
A longstanding goal of the field of AI is a method for learning a highly capable, generalist
agent from diverse experience. In the subfields of vision and language, this was largely …
agent from diverse experience. In the subfields of vision and language, this was largely …
Principled reinforcement learning with human feedback from pairwise or k-wise comparisons
We provide a theoretical framework for Reinforcement Learning with Human Feedback
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
Is conditional generative modeling all you need for decision-making?
Recent improvements in conditional generative modeling have made it possible to generate
high-quality images from language descriptions alone. We investigate whether these …
high-quality images from language descriptions alone. We investigate whether these …
Offline reinforcement learning with implicit q-learning
Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that
improves over the behavior policy that collected the dataset, while at the same time …
improves over the behavior policy that collected the dataset, while at the same time …
Diffusion policies as an expressive policy class for offline reinforcement learning
Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously
collected static dataset, is an important paradigm of RL. Standard RL methods often perform …
collected static dataset, is an important paradigm of RL. Standard RL methods often perform …
A survey of zero-shot generalisation in deep reinforcement learning
The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …
produce RL algorithms whose policies generalise well to novel unseen situations at …