Reinforcement Learning
Divergence-Augmented Policy Optimization
Qing Wang, Yingru Li, Jiechao Xiong, Tong Zhang
In deep reinforcement learning, policy optimization methods need to deal with issues such asfunction approximation andthereuse ofoff-policydata.
Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning
Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of offline RL. However, its reliance on iterative denoising sampling to generate actions slows down both training and inference.
Goal-conditioned Imitation Learning
Yiming Ding, Carlos Florensa, Pieter Abbeel, Mariano Phielipp
Neural Information Processing Systems http://nips.cc/
Learning Safe Policies with Expert Guidance
Jessie Huang, Fa Wu, Doina Precup, Yang Cai
Neural Information Processing Systems http://nips.cc/
DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning
Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang
Neural Information Processing Systems http://nips.cc/
Discovering Creative Behaviors through DUPLEX: Diverse Universal Features for Policy Exploration
The ability to approach the same problem from different angles is a cornerstone of human intelligence that leads to robust solutions and effective adaptation to problem variations. In contrast, current RL methodologies tend to lead to policies that settle on a single solution to a given problem, making them brittle to problem variations. Replicating human flexibility in reinforcement learning agents is the challenge that we explore in this work.
Geometric Algebra Transformer
Such data can take numerous forms, for instance points, direction vectors, translations, or rotations, but to date there is no single architecture that can be applied to such a wide variety of geometric types while respecting their symmetries. In this paper we introduce the Geometric Algebra Transformer (GA Tr), a general-purpose architecture for geometric data.
Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
The key ingredient to MixTURE's success is automatically learning
StabilizingOff-PolicyQ-LearningviaBootstrapping ErrorReduction
One of the primary drivers of the success of machine learning methods in open-world perception settings, such ascomputer vision [19]and NLP [8],has been the ability ofhigh-capacity function approximators, suchasdeepneuralnetworks,tolearngeneralizable modelsfromlargeamountsof data.