LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning

By Yali Du, Lei Han, Meng Fang, Ji Liu, Tianhong Dai, Dacheng Tao. 2019

194 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, methodology): “As a bi-level optimization process, LIIR is signiﬁcantly less computationally eﬃcient than QMIX and has not been demonstrated to scale to large numbers of agents.”
Weighted QMIX: Expanding Monotonic Value Function Factorisation (2020, methodology): “These actor-critic based approaches (as well as COMA [9] and LIIR [5]) do not restrict the class of joint action Q -values they can represent, which theoretically allows them to learn an optimal value function and policy.”
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks (2020, methodology): “These algorithm classes are frequently used in the literature either as baselines or building blocks for more complex algorithms [He et al., 2016, Sukhbaatar et al., 2016, Foerster et al., 2016, Raileanu et al., 2018, Jaques et al., 2019, Iqbal and Sha, 2019, Du et al., 2019, Ryu et al., 2020].”
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2018, methodology): “Learning Individual Intrinsic Reward (LIIR) (Du et al., 2019) learns an intrinsic reward function for each agent to supplement the team reward.”
FACMAC: Factored Multi-Agent Centralised Policy Gradients (2020, methodology): “Most state-of-the-art multi-agent actor-critic methods [21, 7, 11, 6] learn a centralised and monolithic critic conditioning on the global state and the joint action to stabilise learning.”
Comparative Evaluation of Multi-Agent Deep Reinforcement Learning Algorithms (2020, background): “These algorithm classes are frequently used in the literature either as baselines or building blocks for more complex algorithms [8, 11, 13, 15, 17, 27, 29, 32].”
QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning (2020, methodology): “To train agents under the CTDE paradigm, both policy-based (Foerster et al., 2018; Lowe et al., 2017; Du et al., 2019; Iqbal and Sha, 2019; Wang et al., 2020b) and value-based methods (Sunehag et al., 2018; Rashid et al., 2018; Son et al., 2019; Yang et al., 2020) have been proposed.”
The Emergence of Individuality in Multi-Agent Reinforcement Learning (2020, methodology): “Existing methods for reward shaping in MARL focus on independent learning agents e.g. , [3, 27, 28].”