Search Results - "Jiang, Minqi"

General intelligence requires rethinking exploration by Jiang, Minqi, Rocktäschel, Tim, Grefenstette, Edward

“…We are at the cusp of a transition from 'learning from data' to 'learning what data to learn from' as a central focus of artificial intelligence (AI) research…”
Get full text

Study on the effect of sample shapes on the thermal shock behavior of ZrB2‐SiC‐Graphite sharp leading edge by Wang, Anzhe, Liao, Hailong, Zhang, Tao, Jiang, Minqi, Guo, Fuxiao, Wang, Yongzheng

“…Reliable evaluation of the thermal shock behavior of sharp leading edges (SLEs) was hampered by a lack of available experimental method in past decades…”
Get full text

Tailoring the Properties of UiO-66 through Defect Engineering: A Review by Feng, Yi, Chen, Qian, Jiang, Minqi, Yao, Jianfeng

“…Defects, which are commonly in metal organic frameworks (MOFs), are closely related to the performance of materials in various applications. Unlike other MOFs…”
Get full text

An improved Stacking framework for stock index prediction by leveraging tree-based ensemble models and deep learning algorithms by Jiang, Minqi, Liu, Jiapeng, Zhang, Lu, Liu, Chunyu

“…Stock price index is an essential component of financial systems and indicates the economic performance in the national level. Even if a small improvement in…”
Get full text

An extended regularized Kalman filter based on Genetic Algorithm: Application to dynamic asset pricing models by Jiang, Minqi, Liu, Jiapeng, Zhang, Lu

“…•Our approach, namely GA-ErgKF, is capable of tracking the unobserved time-varying parameters under the mixture noise pattern that contains both Gaussian noise…”
Get full text

Learning Curricula in Open-Ended Worlds by Jiang, Minqi

“…Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can…”
Get full text

Learning to Act without Actions by Schmidt, Dominik, Jiang, Minqi

“…Pre-training large models on vast amounts of web data has proven to be an effective approach for obtaining powerful, general models in domains such as language…”
Get full text

Study on the effect of sample shapes on the thermal shock behavior of ZrB 2 ‐SiC‐Graphite sharp leading edge by Wang, Anzhe, Liao, Hailong, Zhang, Tao, Jiang, Minqi, Guo, Fuxiao, Wang, Yongzheng

“…Abstract Reliable evaluation of the thermal shock behavior of sharp leading edges (SLEs) was hampered by a lack of available experimental method in past…”
Get full text

Anomaly Detection with Score Distribution Discrimination by Jiang, Minqi, Han, Songqiao, Huang, Hailiang

“…Recent studies give more attention to the anomaly detection (AD) methods that can leverage a handful of labeled anomalies along with abundant unlabeled data…”
Get full text

Reward-Free Curricula for Training Robust World Models by Rigter, Marc, Jiang, Minqi, Posner, Ingmar

“…There has been a recent surge of interest in developing generally-capable agents that can adapt to new tasks without additional training in the environment…”
Get full text

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs by Henaff, Mikael, Jiang, Minqi, Raileanu, Roberta

“…Exploration in environments which differ across episodes has received increasing attention in recent years. Current methods use some combination of global…”
Get full text

General Intelligence Requires Rethinking Exploration by Jiang, Minqi, Rocktäschel, Tim, Grefenstette, Edward

“…We are at the cusp of a transition from "learning from data" to "learning what data to learn from" as a central focus of artificial intelligence (AI) research…”
Get full text

The Generalization Gap in Offline Reinforcement Learning by Mediratta, Ishita, You, Qingfei, Jiang, Minqi, Raileanu, Roberta

“…Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization…”
Get full text

minimax: Efficient Baselines for Autocurricula in JAX by Jiang, Minqi, Dennis, Michael, Grefenstette, Edward, Rocktäschel, Tim

“…Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen…”
Get full text

Exploration via Elliptical Episodic Bonuses by Henaff, Mikael, Raileanu, Roberta, Jiang, Minqi, Rocktäschel, Tim

“…In recent years, a number of reinforcement learning (RL) methods have been proposed to explore complex environments which differ across episodes. In this work,…”
Get full text

GriddlyJS: A Web IDE for Reinforcement Learning by Bamford, Christopher, Jiang, Minqi, Samvelyan, Mikayel, Rocktäschel, Tim

“…Progress in reinforcement learning (RL) research is often driven by the design of new, challenging environments -- a costly undertaking requiring skills…”
Get full text

Refining Minimax Regret for Unsupervised Environment Design by Beukman, Michael, Coward, Samuel, Matthews, Michael, Fellows, Mattie, Jiang, Minqi, Dennis, Michael, Foerster, Jakob

“…In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises…”
Get full text

Prioritized Level Replay by Jiang, Minqi, Grefenstette, Edward, Rocktäschel, Tim

“…Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this…”
Get full text

Multi-Agent Diagnostics for Robustness via Illuminated Diversity by Samvelyan, Mikayel, Paglieri, Davide, Jiang, Minqi, Parker-Holder, Jack, Rocktäschel, Tim

“…In the rapidly advancing field of multi-agent systems, ensuring robustness in unfamiliar and adversarial settings is crucial. Notwithstanding their outstanding…”
Get full text

ADGym: Design Choices for Deep Anomaly Detection by Jiang, Minqi, Hou, Chaochuan, Zheng, Ao, Han, Songqiao, Huang, Hailiang, Wen, Qingsong, Hu, Xiyang, Zhao, Yue

“…Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud…”
Get full text