ATSIS: Achieving the Ad hoc Teamwork by Sub-task Inference and Selection

Chen, Shuo; Andrejczuk, Ewa; Irissappane, Athirai A.; Zhang, Jie

doi:10.24963/ijcai.2019/25

Cited by 5 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others have looked at multi-agent scenarios that do not allow for a full prior coordination or centralized control, but instead require agents to adapt to each other individually and dynamically, and even establish a form of "ad-hoc teamwork" [21][22][23]. This problem of on-the-fly coordination has recently become prominent in collaborative robots and service robots [24] and has been approached mostly for attention and motor-level coordination of physical tasks between humans and robots, e.g., when handing over objects or jointly carrying them [24].…”

Section: Related Work and Backgroundmentioning

confidence: 99%

Resonating Minds—Emergent Collaboration Through Hierarchical Active Inference

2021

View full text Add to dashboard Cite

Working together on complex collaborative tasks requires agents to coordinate their actions. Doing this explicitly or completely prior to the actual interaction is not always possible nor sufficient. Agents also need to continuously understand the current actions of others and quickly adapt their own behavior appropriately. Here we investigate how efficient, automatic coordination processes at the level of mental states (intentions, goals), which we call belief resonance, can lead to collaborative situated problem-solving. We present a model of hierarchical active inference for collaborative agents (HAICA). It combines efficient Bayesian Theory of Mind processes with a perception–action system based on predictive processing and active inference. Belief resonance is realized by letting the inferred mental states of one agent influence another agent’s predictive beliefs about its own goals and intentions. This way, the inferred mental states influence the agent’s own task behavior without explicit collaborative reasoning. We implement and evaluate this model in the Overcooked domain, in which two agents with varying degrees of belief resonance team up to fulfill meal orders. Our results demonstrate that agents based on HAICA achieve a team performance comparable to recent state-of-the-art approaches, while incurring much lower computational costs. We also show that belief resonance is especially beneficial in settings where the agents have asymmetric knowledge about the environment. The results indicate that belief resonance and active inference allow for quick and efficient agent coordination and thus can serve as a building block for collaborative cognitive agents.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

Resonating Minds—Emergent Collaboration Through Hierarchical Active Inference

2021

View full text Add to dashboard Cite

show abstract

“…1 (red flags). The domain-specific g can be designed by learning-based offline training (Jaderberg et al 2016;Eysenbach, Salakhutdinov, and Levine 2019) or rule-based online reasoning (Kurzer, Zhou, and Zöllner 2018;Chen et al 2019a;Gabor et al 2019). We design rule-based g for fully-online planning.…”

Section: Subgoal-based Protocol For Coordination Subgoal Predicatementioning

confidence: 99%

“…Third, it is worthy to mention Ad Hoc Teamwork (Stone et al 2010;Chen et al 2019a), where an agent engages in collaborative tasks without relying on communication or pre-defined strategy. However, without communication, it may rely on much offline training instead for understanding teammates, e.g.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Dec-SGTS: Decentralized Sub-Goal Tree Search for Multi-Agent Coordination

Cai

Yang

et al. 2021

AAAI

View full text Add to dashboard Cite

Multi-agent coordination tends to benefit from efficient communication, where cooperation often happens based on exchanging information about what the agents intend to do, i.e. intention sharing. It becomes a key problem to model the intention by some proper abstraction. Currently, it is either too coarse such as final goals or too fined as primitive steps, which is inefficient due to the lack of modularity and semantics. In this paper, we design a novel multi-agent coordination protocol based on subgoal intentions, defined as the probability distribution over feasible subgoal sequences. The subgoal intentions encode macro-action behaviors with modularity so as to facilitate joint decision making at higher abstraction. Built over the proposed protocol, we present Dec-SGTS (Decentralized Sub-Goal Tree Search) to solve decentralized online multi-agent planning hierarchically and efficiently. Each agent runs Dec-SGTS asynchronously by iteratively performing three phases including local sub-goal tree search, local subgoal intention update and global subgoal intention sharing. We conduct the experiments on courier dispatching problem, and the results show that Dec-SGTS achieves much better reward while enjoying a significant reduction of planning time and communication cost compared with Dec-MCTS (Decentralized Monte Carlo Tree Search).

show abstract

“…As for the second simplification, assuming a fullyobservable action space limits the potential on real-life applications. The researchers develop algorithms to plan the ad hoc agent's action either by using the past teammates' behaviour types (Wu, Zilberstein, and Chen 2011;Albrecht and Ramamoorthy 2013;Barrett et al 2013;Melo and Sardinha 2016;Chandrasekaran et al 2017;Ravula, Alkoby, and Stone 2019) or by inferring the responsibilities new teammates are taking (Chen et al 2019). In both cases, they assume that teammates' actions are fully observable, which is a strong assumption when it comes to more complex domains (e.g.…”

Section: Related Workmentioning

confidence: 99%

AATEAM: Achieving the Ad Hoc Teamwork by Employing the Attention Mechanism

Chen

Andrejczuk

Cao

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

In the ad hoc teamwork setting, a team of agents needs to perform a task without prior coordination. The most advanced approach learns policies based on previous experiences and reuses one of the policies to interact with new teammates. However, the selected policy in many cases is sub-optimal. Switching between policies to adapt to new teammates' behaviour takes time, which threatens the successful performance of a task. In this paper, we propose AATEAM – a method that uses the attention-based neural networks to cope with new teammates' behaviour in real-time. We train one attention network per teammate type. The attention networks learn both to extract the temporal correlations from the sequence of states (i.e. contexts) and the mapping from contexts to actions. Each attention network also learns to predict a future state given the current context and its output action. The prediction accuracies help to determine which actions the ad hoc agent should take. We perform extensive experiments to show the effectiveness of our method.

show abstract

ATSIS: Achieving the Ad hoc Teamwork by Sub-task Inference and Selection

Cited by 5 publications

References 11 publications

Resonating Minds—Emergent Collaboration Through Hierarchical Active Inference

Resonating Minds—Emergent Collaboration Through Hierarchical Active Inference

Dec-SGTS: Decentralized Sub-Goal Tree Search for Multi-Agent Coordination

AATEAM: Achieving the Ad Hoc Teamwork by Employing the Attention Mechanism

Contact Info

Product

Resources

About