Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Rashid, Tabish"'
Training agents to behave as desired in complex 3D environments from high-dimensional sensory information is challenging. Imitation learning from diverse human behavior provides a scalable approach for training an agent with a sensible behavioral pri
Externí odkaz:
http://arxiv.org/abs/2406.04208
Autor:
Schäfer, Lukas, Jones, Logan, Kanervisto, Anssi, Cao, Yuhan, Rashid, Tabish, Georgescu, Raluca, Bignell, Dave, Sen, Siddhartha, Gavito, Andrea Treviño, Devlin, Sam
Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community. Recent progress in
Externí odkaz:
http://arxiv.org/abs/2312.02312
Autor:
Pearce, Tim, Rashid, Tabish, Kanervisto, Anssi, Bignell, Dave, Sun, Mingfei, Georgescu, Raluca, Macua, Sergio Valcarcel, Tan, Shan Zheng, Momennejad, Ida, Hofmann, Katja, Devlin, Sam
Publikováno v:
ICLR 2023
Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and
Externí odkaz:
http://arxiv.org/abs/2301.10677
Tackling overestimation in $Q$-learning is an important problem that has been extensively studied in single-agent reinforcement learning, but has received comparatively little attention in the multi-agent setting. In this work, we empirically demonst
Externí odkaz:
http://arxiv.org/abs/2103.11883
Game theory has been increasingly applied in settings where the game is not known outright, but has to be estimated by sampling. For example, meta-games that arise in multi-agent evaluation can only be accessed by running a succession of expensive ex
Externí odkaz:
http://arxiv.org/abs/2101.09178
QMIX is a popular $Q$-learning algorithm for cooperative MARL in the centralised training and decentralised execution paradigm. In order to enable easy decentralisation, QMIX restricts the joint action $Q$-values it can represent to be a monotonic mi
Externí odkaz:
http://arxiv.org/abs/2006.10800
Autor:
Rashid, Tabish, Samvelyan, Mikayel, de Witt, Christian Schroeder, Farquhar, Gregory, Foerster, Jakob, Whiteson, Shimon
Publikováno v:
Journal of Machine Learning Research 21(178):1-51, 2020
In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and c
Externí odkaz:
http://arxiv.org/abs/2003.08839
Autor:
Peng, Bei, Rashid, Tabish, de Witt, Christian A. Schroeder, Kamienny, Pierre-Alexandre, Torr, Philip H. S., Böhmer, Wendelin, Whiteson, Shimon
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. Like MADDPG, a popular multi-agent actor-critic method, our approach
Externí odkaz:
http://arxiv.org/abs/2003.06709
Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algorithms do not use optimistic in
Externí odkaz:
http://arxiv.org/abs/2002.12174
Publikováno v:
Advances in Neural Information Processing Systems, 32, 2019, 7611-7622
Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper, we analyse
Externí odkaz:
http://arxiv.org/abs/1910.07483