Efficient Imitation Learning with Conservative World Models
We tackle the problem of policy learning from expert demonstrations without a reward
function. A central challenge in this space is that these policies fail upon deployment due to …
function. A central challenge in this space is that these policies fail upon deployment due to …
SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation
Autonomous self-improving robots that interact and improve with experience are key to the
real-world deployment of robotic systems. In this paper, we propose an online learning …
real-world deployment of robotic systems. In this paper, we propose an online learning …
Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
Combining offline and online reinforcement learning (RL) techniques is indeed crucial for
achieving efficient and safe learning where data acquisition is expensive. Existing methods …
achieving efficient and safe learning where data acquisition is expensive. Existing methods …
A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms
We devise a control-theoretic reinforcement learning approach to support direct learning of
the optimal policy. We establish theoretical properties of our approach and derive an …
the optimal policy. We establish theoretical properties of our approach and derive an …
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Q Wang, J Yang, Y Wang, X Jin, W Zeng… - arXiv preprint arXiv …, 2023 - arxiv.org
Training offline reinforcement learning (RL) models using visual inputs poses two significant
challenges, ie, the overfitting problem in representation learning and the overestimation bias …
challenges, ie, the overfitting problem in representation learning and the overestimation bias …
Collaborative World Models: An Online-Offline Transfer RL Approach
Training offline reinforcement learning (RL) models with visual inputs is challenging due to
the coupling of overfitting issue in representation learning and the risk of overestimating true …
the coupling of overfitting issue in representation learning and the risk of overestimating true …
Guided Decoupled Exploration for Offline Reinforcement Learning Fine-tuning
Fine-tuning pre-trained offline Reinforcement Learning (RL) agents with online interactions
is a promising strategy to improve the sample efficiency. In this work, we study the problem …
is a promising strategy to improve the sample efficiency. In this work, we study the problem …