Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges
Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI)
technique. However, current studies and applications need to address its scalability, non …
technique. However, current studies and applications need to address its scalability, non …
Loss of plasticity in continual deep reinforcement learning
In this paper, we characterize the behavior of canonical value-based deep reinforcement
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …
Concept activation regions: A generalized framework for concept-based explanations
J Crabbé, M van der Schaar - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Concept-based explanations permit to understand the predictions of a deep neural
network (DNN) through the lens of concepts specified by users. Existing methods assume …
network (DNN) through the lens of concepts specified by users. Existing methods assume …
A survey of progress on cooperative multi-agent reinforcement learning in open environment
Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …
has made progress in various fields. Specifically, cooperative MARL focuses on training a …
[图书][B] Distributional reinforcement learning
The first comprehensive guide to distributional reinforcement learning, providing a new
mathematical formalism for thinking about decisions from a probabilistic perspective …
mathematical formalism for thinking about decisions from a probabilistic perspective …
Visibility into AI Agents
Increased delegation of commercial, scientific, governmental, and personal activities to AI
agents—systems capable of pursuing complex goals with limited supervision—may …
agents—systems capable of pursuing complex goals with limited supervision—may …
Entanglement entropy production in quantum neural networks
Abstract Quantum Neural Networks (QNN) are considered a candidate for achieving
quantum advantage in the Noisy Intermediate Scale Quantum computer (NISQ) era. Several …
quantum advantage in the Noisy Intermediate Scale Quantum computer (NISQ) era. Several …
Maximum diffusion reinforcement learning
Robots and animals both experience the world through their bodies and senses. Their
embodiment constrains their experiences, ensuring that they unfold continuously in space …
embodiment constrains their experiences, ensuring that they unfold continuously in space …
Deep learning opacity in scientific discovery
E Duede - Philosophy of Science, 2023 - cambridge.org
While philosophers have focused on epistemological and ethical challenges of using
artificial intelligence (AI) in science, scientists have focused largely on opportunities. I argue …
artificial intelligence (AI) in science, scientists have focused largely on opportunities. I argue …
Constrained policy optimization with explicit behavior density for offline reinforcement learning
Due to the inability to interact with the environment, offline reinforcement learning (RL)
methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing …
methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing …