A signal-centric perspective on the evolution of symbolic communication

Lotito, Quintino Francesco; Custode, Leonardo Lucio; Iacca, Giovanni

doi:10.1145/3449639.3459273

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work includes: 1) evaluating the proposed approach on different tasks; 2) introducing the possibility of communication between agents (both symbolic [32] and sub-symbolic [33]); 3) designing more efficient methodologies for training interpretable MARL systems, including for instance using other RL algorithms (different from Q-learning), and comparing them with existing methods, as well as handmade problem-specific policies; and 4) performing a sensitivity analysis for the proposed method.…”

Section: Discussionmentioning

confidence: 99%

Towards Interpretable Policies in Multi-agent Reinforcement Learning Tasks

Crespi

Custode²,

Iacca³

2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Deep Learning (DL) allowed the field of Multi-Agent Reinforcement Learning (MARL) to make significant advances, speeding-up the progress in the field. However, agents trained by means of DL in MARL settings have an important drawback: their policies are extremely hard to interpret, not only at the individual agent level, but also (and especially) considering the fact that one has to take into account the interactions across the whole set of agents. In this work, we make a step towards achieving interpretability in MARL tasks. To do that, we present an approach that combines evolutionary computation (i.e., grammatical evolution) and reinforcement learning (Q-learning), which allows us to produce agents that are, at least to some extent, understandable. Moreover, differently from the typically centralized DL-based approaches (and because of the possibility to use a replay buffer), in our method we can easily employ Independent Q-learning to train a team of agents, which facilitates robustness and scalability. By evaluating our approach on the Battlefield task from the MAgent implementation in the PettingZoo library, we observe that the evolved team of agents is able to coordinate its actions in a distributed fashion, solving the task in an effective way.

show abstract

Section: Discussionmentioning

confidence: 99%