Coordinated behavior of cooperative agents using deep reinforcement learning

Diallo, Elhadji Amadou Oury; Sugiyama, Ayumi; Sugawara, Toshiharu

doi:10.1016/j.neucom.2018.08.094

Cited by 17 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scientists have been working on extending reinforcement learning (RL) to MASs to identify appropriate behavior in complex systems. Markov games 94 have been widely recognized as the prevalent model of multi-agent reinforcement learning (MARL). MARL is the learning technique of multiple agents trying to maximize their expected total discounted reward while coexisting within a Markov game environment whose underlying transition and reward models are usually unknown or noisy.…”

Section: Musv Collaborative Round-up Methodsmentioning

confidence: 99%

Review of multiple unmanned surface vessels collaborative search and hunting based on swarm intelligence

Sun

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In recent years, the research of multiple unmanned surface vessels collaboration has received great attention. More and more researchers have proposed different methods of multiple unmanned surface vessels collaboration, such as cooperative collision avoidance, formation, and rendezvous. Based on the significant advantages of biological swarm intelligence applications in these collaborative methods, this article summarizes the research methods of multiple unmanned surface vessels collaborative search and hunting from the perspective of swarm intelligence. First of all, this article summarizes the key technologies of multiple unmanned surface vessels collaborative search and hunting from the aspects of the multi-robot system, group communication, environment modeling, collaboration mechanism, and path planning. Then, it reviews some classic swarm intelligence algorithms, analyzes the advantages and disadvantages of these algorithms, and proposes optimization directions for existing disadvantages based on relevant literature. Finally, the article points out some existing problems in every stage and suggestions for future research.

show abstract

Section: Musv Collaborative Round-up Methodsmentioning

confidence: 99%

Review of multiple unmanned surface vessels collaborative search and hunting based on swarm intelligence

Sun

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Specifically, the authors study how manipulating the reward function affected the progression of cooperation and competition between independent Q-learners [19]. Another related study [20], shows that agents could learn cooperative strategies in the same two-player pong game using only raw pixel data, even within a non-stationary environment. We base our study on these two papers while focusing only on the cooperative side of the spectrum.…”

Section: Related Workmentioning

confidence: 99%

Learning to Cooperate with Human Evaluative Feedback and Demonstrations

Verma

Acar

2022

HHAI2022: Augmenting Human Intellect

View full text Add to dashboard Cite

Cooperation is a widespread phenomenon in nature that has also been a cornerstone in the development of human intelligence. Understanding cooperation, therefore, on matters such as how it emerges, develops, or fails is an important avenue of research, not only in a human context, but also for the advancement of next generation artificial intelligence paradigms which are presumably human-compatible. With this motivation in mind, we study the emergence of cooperative behaviour between two independent deep reinforcement learning (RL) agents provided with human input in a novel game environment. In particular, we investigate whether evaluative human feedback (through interactive RL) and expert demonstration (through inverse RL) can help RL agents to learn to cooperate better. We report two main findings. Firstly, we find that the amount of feedback given has a positive impact on the accumulated reward obtained through cooperation. That is, agents trained with a limited amount of feedback outperform agents trained without any feedback, and the performance increases even further as more feedback is provided. Secondly, we find that expert demonstration also helps agents’ performance, although with more modest improvements compared to evaluative feedback. In conclusion, we present a novel game environment to better understand the emergence of cooperative behaviour and show that providing human feedback and demonstrations can accelerate this process.

show abstract

“…In the DRL framework, deep learning provides the agent with the ability to sense the environment and reinforcement learning provides the ability to learn the best strategy for real-time problems [48]. DRL enables creating an agent that can generalize to an environment that is examined as meta-learning [49]. As a generic way of solving optimization problems through trial and error, DRL finds its application in several fields like agriculture [50], health care [51], energy management [52], robotic system [53] and game theory [54].…”

Section: Related Workmentioning

confidence: 99%

Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications

2020

View full text Add to dashboard Cite

Predicting crop yield based on the environmental, soil, water and crop parameters has been a potential research topic. Deep-learning-based models are broadly used to extract significant crop features for prediction. Though these methods could resolve the yield prediction problem there exist the following inadequacies: Unable to create a direct non-linear or linear mapping between the raw data and crop yield values; and the performance of those models highly relies on the quality of the extracted features. Deep reinforcement learning provides direction and motivation for the aforementioned shortcomings. Combining the intelligence of reinforcement learning and deep learning, deep reinforcement learning builds a complete crop yield prediction framework that can map the raw data to the crop prediction values. The proposed work constructs a Deep Recurrent Q-Network model which is a Recurrent Neural Network deep learning algorithm over the Q-Learning reinforcement learning algorithm to forecast the crop yield. The sequentially stacked layers of Recurrent Neural network is fed by the data parameters. The Q-learning network constructs a crop yield prediction environment based on the input parameters. A linear layer maps the Recurrent Neural Network output values to the Q-values. The reinforcement learning agent incorporates a combination of parametric features with the threshold that assist in predicting crop yield. Finally, the agent receives an aggregate score for the actions performed by minimizing the error and maximizing the forecast accuracy. The proposed model efficiently predicts the crop yield outperforming existing models by preserving the original data distribution with an accuracy of 93.7%.INDEX TERMS Crop yield prediction, deep recurrent Q-network, deep reinforcement learning, intelligent agrarian application.

show abstract

Coordinated behavior of cooperative agents using deep reinforcement learning

Cited by 17 publications

References 18 publications

Review of multiple unmanned surface vessels collaborative search and hunting based on swarm intelligence

Review of multiple unmanned surface vessels collaborative search and hunting based on swarm intelligence

Learning to Cooperate with Human Evaluative Feedback and Demonstrations

Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications

Contact Info

Product

Resources

About