While Reinforcement Learning (RL) achieves tremendous success in sequential decision- making problems of many domains, it still faces key challenges of data inefficiency and the …
Learning reward-agnostic representations is an emerging paradigm in reinforcement learning. These representations can be leveraged for several purposes ranging from reward …
D Freirich, T Shimkin, R Meir… - … Conference on Machine …, 2019 - proceedings.mlr.press
The recently proposed distributional approach to reinforcement learning (DiRL) is centered on learning the distribution of the reward-to-go, often referred to as the value distribution. In …
Z Zhu, H Zhao, H He, Y Zhong, S Zhang, Y Yu… - arXiv preprint arXiv …, 2023 - arxiv.org
Diffusion models have emerged as a prominent class of generative models, surpassing previous methods regarding sample quality and training stability. Recent works have shown …
Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards. In particular, this requires separating skill from luck, ie …
Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future …
Z Lin, L Zhao, D Yang, T Qin… - Advances in neural …, 2019 - proceedings.neurips.cc
Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and …
Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying …
S Alver, D Precup - arXiv preprint arXiv:2112.15025, 2021 - arxiv.org
We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little …