Skip to search formSkip to main contentSkip to account menu

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

MALib is a scalable and efficient computing framework for population-based multi-agent reinforcement learning that enables efficient code reuse and flexible deployments on different distributed computing paradigms and achieves throughput higher than 40K FPS on a single machine with 32 CPU cores.
View PDF on arXiv (opens in a new tab)

Towards Efficient Discrete Integration via Adaptive Quantile Queries

AdaWISH is proposed, which is able to obtain the same guarantee but accesses only a small subset of queries of WISH, and has a regret of only O(log n) relative to an idealistic oracle that issues queries at data-dependent optimal points.
View PDF on arXiv (opens in a new tab)

Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition

This paper proposes a novel training strategy by introducing a majority model and a minority model based on the epistemic uncertainty that achieves the state-of-the-art per-formance under both sufficient and insufficient data.
View on IEEE (opens in a new tab)

AdaWISH: Faster Discrete Integration via Adaptive Quantiles

AdaWISH is proposed, which is able to obtain the same guarantee, but accesses only a small subset of queries of WISH, and has a regret of no more than $O(\log n)$ relative to an oracle that issues queries at data-dependent optimal points.

Variational message passing neural network for Maximum-A-Posteriori (MAP) inference

A variational message passing neural network (V-MPNN), where both the power of neural networks in modeling complex functions and the well-established algorithmic theories on variational belief propagation are leveraged.
View Paper (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)