Tabish Rashid

Microsoft Research (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

14h-index2.2kcitations27works3.32yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(19), Adversarial Robustness in Machine Learning(4), Auction Theory and Applications(3), Advanced Bandit Algorithms Research(3), Adaptive Dynamic Programming Control(3)

Publications27 total

A fine-grained multi-lingual opinion mining method on social media texts using multi-scale fused features-based adaptive residual convolutional LSTM with attention mechanism
Data & Knowledge Engineering·2025
World and Human Action Models towards gameplay ideation
Nature·2025· 11 citedOpen Access
Scaling Laws for Pre-training Agents and World Models
arXiv (Cornell University)·2024· 2 citedOpen Access
Aligning Agents like Large Language Models
arXiv (Cornell University)·2024Open Access
Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games
arXiv (Cornell University)·2023· 1 citedOpen Access
Imitating Human Behaviour with Diffusion Models
arXiv (Cornell University)·2023· 23 citedOpen Access
FACMAC: Factored Multi−Agent Centralised Policy Gradients
Oxford University Research Archive (ORA) (University of Oxford)·2021Open Access
Regularized Softmax Deep Multi−Agent Q−Learning
Oxford University Research Archive (ORA) (University of Oxford)·2021
Estimating α-Rank by Maximizing Information Gain
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 4 citedOpen Access
Regularized Softmax Deep Multi-Agent $Q$-Learning
arXiv (Cornell University)·2021· 16 citedOpen Access
Softmax with Regularization: Better Value Estimation in Multi-Agent Reinforcement Learning.
arXiv (Cornell University)·2021· 3 citedOpen Access
Estimating $α$-Rank by Maximizing Information Gain
arXiv (Cornell University)·2021Open Access
Estimating $\alpha$-Rank by Maximizing Information Gain.
arXiv (Cornell University)·2021Open Access
Exploration and value function factorisation in single and multi-agent reinforcement learning
Oxford University Research Archive (ORA) (University of Oxford)·2021Open Access
Weighted QMIX: Expanding Monotonic Value Function Factorisation.
arXiv (Cornell University)·2020· 22 citedOpen Access
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2020· 37 citedOpen Access
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2020· 429 citedOpen Access
FACMAC: Factored Multi-Agent Centralised Policy Gradients
arXiv (Cornell University)·2020· 106 citedOpen Access
Optimistic Exploration even with a Pessimistic Initialisation
arXiv (Cornell University)·2020· 13 citedOpen Access
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep\n Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2020· 114 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Shimon Whiteson(16), Gregory Farquhar(8), Bei Peng(7), Mikayel Samvelyan(6), Christian Schroeder de Witt(5), Jakob Foerster(5), Dave Bignell(5), Sam Devlin(5), Philip H. S. Torr(4), Anssi Kanervisto(3), Raluca Georgescu(3), Katja Hofmann(3), Ling Pan(3), Longbo Huang(3), Yuhan Cao(3), Kamil Ciosek(3), Nantas Nardelli(2), Tim G. J. Rudner(2), Chia-Man Hung(2), Pierre-Alexandre Kamienny(2)