Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks

2016-02-08 · Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson

We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is the first time deep reinforcement learning has succeeded in learning communication protocols. In addition, we present ablation experiments that confirm that each of the main components of the DDRQN architecture are critical to its success.

📄 PDF Abstract BibTeX arXiv:1602.02672

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

CC-Riddle: A Question Answering Dataset of Chinese Character Riddles

2022-06-28 · Fan Xu, Yunxiang Zhang, Xiaojun Wan

The Chinese character riddle is a unique form of cultural entertainment specific to the Chinese language. It typically comprises two parts: the riddle description and the solution. The solution to the riddle is a single …

General Knowledge Language Modelling Multiple-choice Question Answering

Riddle Quest : The Enigma of Words

2026-01-27 · Niharika Sri Parasa, Chaitali Diwan, Srinath Srinivasa arxiv

Riddles are concise linguistic puzzles that describe an object or idea through indirect, figurative, or playful clues. They are a longstanding form of creative expression, requiring the solver to interpret hints, recogni…

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

2016-05-21 · NeurIPS 2016 12 · Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share informati…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Automatically generating Riddles aiding Concept Attainment

2023-10-27 · Niharika Sri Parasa, Chaitali Diwan, Srinath Srinivasa

One of the primary challenges in online learning environments, is to retain learner engagement. Several different instructional strategies are proposed both in online and offline environments to enhance learner engagemen…

Riddle Generation using Word Associations

2016-05-01 · LREC 2016 5 · Paloma Galv{\'a}n, Virginia Francisco, Raquel Herv{\'a}s, Gonzalo M{\'e}ndez

In knowledge bases where concepts have associated properties, there is a large amount of comparative information that is implicitly encoded in the values of the properties these concepts share. Although there have been p…