Hierarchical reinforcement learning in communication-mediated multiagent coordination
By Felix A. Fischer, Michael Rovatsos, Gerhard Weiss. 2004
32 citations recorded by the source corpus.
Over the past decade, reinforcement learning (RL; e.g., see [9]) has been an active area of AI research in general and of research on agents and multiagent systems (MASs) in particular. In the originalMarkov decision process (MDP; e.g., see [5]) formulation of RL, other agents an agent is coexisting and interacting with are treated as part of its environment. The inability of MDPs to model multiple adaptive agents has explicitly been identified as the main drawback of this approach [4]. As a consequence, interest has grown in extending the RL framework to explicitly take into account other agents as autonomous and self-interested entities (see [8] for an overview). In this paper, we follow this line of research while focussing on communication-mediated multiagent coordination problems. The idea here is that “physical” acting can be preceded by communication to allow for a prediction of actions to come. By assuming that this kind of communication does not manipulate the environment (i.e. hardly affects the states agents find themselves in) and does not have effects w.r.t. utility, we can view the exchanged messages as symbols that “encode” anticipated courses of physical action. This is in accordance with the model of communication we have laid out in [6]. We make two contributions to the solution of communication-mediated multiagent coordination problems:
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Fei Sha
- Robert Babuška
- Lucian Busoniu
- B. Schutter
- Shariq Iqbal
- Shimon Whiteson
- Karl Tuyls
- Maxim Egorov Stanford
In Molecular Biology
Citations in the corpus
- Actor-Attention-Critic for Multi-Agent Reinforcement Learning (2018, background): “Topics within MARL are diverse, ranging from learning communication between cooperative agents (Tan, 1993; Fischer et al., 2004) to algorithms for optimal play in competitive settings (Littman, 1994), though, until recently, they have been focused on simple gridworld environments with tabular…”
- A Comprehensive Survey of Multiagent Reinforcement Learning (2008, background): “Communication can be used to negotiate action choices, either alone or in combination with the above techniques, as in [2], [81].”
- Multi-agent Reinforcement Learning: An Overview (2010, background): “Communication can be used to negotiate action choices, either alone or in combination with the above coordination techniques, as in [37,135].”