Deep Decentralized Multi-task Multi-Agent RL under Partial Observability

By Shayegan Omidshafiei, Jason Pazis, Chris Amato, Jonathan P. How, John L. Vian. 2017

27 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

Counterfactual Multi-Agent Policy Gradients (2017, background): “Omidshaﬁei et al. (2017) also address the stability of experience replay in multi-agent settings, but assume a fully decentralised training regime.”
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, neutral): “Omidshaﬁei et al. (2017) utilises Hysteretic Q -learning in a multi-task deep RL setting.”
D2: Decentralized Training over Decentralized Data (2018, methodology): “The decentralized approach for multi-task reinforcement learning was studied in Mhamdi et al. [2017], Omidshaﬁei et al. [2017].”
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2018, neutral): “Peng et al. (2017) also evaluate their methods on StarCraft.”
Learning with Opponent-Learning Awareness (2017, background): “However, most of this recent work considers fully cooperative settings [13, 14, 34] and emergent”
MAVEN: Multi-Agent Variational Exploration (2019, background): “[12, 35] tackle the instability that arises from training the agents independently.”
Lenient Multi-Agent Deep Reinforcement Learning (2017, methodology): “Furthermore the ﬁrst run failed to converge for the Hybrid version of the SHDQN.”
Communication Compression for Decentralized Training (2018, methodology): “The decentralized structure can applied in solving of multi-task multi-agent reinforcement learning [Omidshaﬁei et al., 2017, Mhamdi et al., 2017].”
Decentralization Meets Quantization (2018, methodology): “The decentralized structure can applied in solving of multi-task multi-agent reinforcement learning [Mhamdi et al., 2017, Omidshafiei et al., 2017].”
Modeling Others using Oneself in Multi-Agent Reinforcement Learning (2018, background): “A large body of work in deep multi-agent RL focuses on partially visible, fully cooperative settings (Foerster et al., 2016a;b; Omidshafiei et al., 2017) and emergent communication (Lazaridou et al.”
Guided Meta-Policy Search (2019, unknown): “…approach is related to multi-task RL methods that seek to distill policies for multiple tasks into a single policy, akin to guided policy search (Levine et al., 2016) and related approaches (Rusu et al., 2016; Parisotto et al., 2016; Teh et al., 2017; Omidshaﬁei et al., 2017; Ghosh et al., 2018).”