Corentin Artaud

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL. While multiple communication methods have been proposed, these might still be too complex and not easily transferable to more practical contexts. One of the reasons for that is due to the use of the famous parameter sharing trick. In this paper, we investigate how independent learners in MARL that do not share parameters can communicate. We demonstrate that this setting might incur into some problems, to which we propose a new learning scheme as a solution. Our results show that, despite the challenges, independent agents can still learn communication strategies following our method. Additionally, we use this method to investigate how communication in MARL is affected by different network capacities, both for sharing and not sharing parameters. We observe that communication may not always be needed and that the chosen agent network sizes need to be considered when used together with communication in order to achieve efficient learning.

Reinforcement Learning (RL) is an area of growing interest in the field of artificial intelligence due to its many notable applications in diverse fields. Particularly within the context of intelligent vehicle control, RL has made impressive progress. However, currently it is still in simulated controlled environments where RL can achieve its full super-human potential. Although how to apply simulation experience in real scenarios has been studied, how to approximate simulated problems to the real dynamic problems is still a challenge. In this paper, we discuss two methods that approximate RL problems to real problems. In the context of traffic junction simulations, we demonstrate that, if we can decompose a complex task into multiple sub-tasks, solving these tasks first can be advantageous to help minimising possible occurrences of catastrophic events in the complex task. From a multi-agent perspective, we introduce a training structuring mechanism that exploits the use of experience learned under the popular paradigm called Centralised Training Decentralised Execution (CTDE). This experience can then be leveraged in fully decentralised settings that are conceptually closer to real settings, where agents often do not have access to a central oracle and must be treated as isolated independent units. The results show that the proposed approaches improve agents performance in complex tasks related to traffic junctions, minimising potential safety-critical problems that might happen in these scenarios. Although still in simulation, the investigated situations are conceptually closer to real scenarios and thus, with these results, we intend to motivate further research in the subject.

Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that denotes the event when some of the agents in a MARL team do not contribute to the common goal, letting the teammates do all the work. In this work, we aim to investigate this problem from a causality-based perspective. We intend to create the bridge between the fields of MARL and causality and argue about the usefulness of this link. We study a fully decentralised MARL setup where agents need to learn cooperation strategies and show that there is a causal relation between individual observations and the team reward. The experiments carried show how this relation can be used to improve independent agents in MARL, resulting not only on better performances as a team but also on the rise of more intelligent behaviours on individual agents.

In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objective of the team. Such agents are called lazy agents due to their non-cooperative behaviours that may arise from failing to understand whether they caused the rewards. As a consequence, we observe that the emergence of cooperative behaviours is not necessarily a byproduct of being able to solve a task as a team. In this paper, we investigate the applications of causality in MARL and how it can be applied in MARL to penalise these lazy agents. We observe that causality estimations can be used to improve the credit assignment to the agents and show how it can be leveraged to improve independent learning in MARL. Furthermore, we investigate how Amortized Causal Discovery can be used to automate causality detection within MARL environments. The results demonstrate that causality relations between individual observations and the team reward can be used to detect and punish lazy agents, making them develop more intelligent behaviours. This results in improvements not only in the overall performances of the team but also in their individual capabilities. In addition, results show that Amortized Causal Discovery can be used efficiently to find causal relations in MARL.

When learning a task as a team, some agents in Multi-Agent Reinforcement Learning (MARL) may fail to understand their true impact in the performance of the team. Such agents end up learning sub-optimal policies, demonstrating undesired lazy behaviours. To investigate this problem, we start by formalising the use of temporal causality applied to MARL problems. We then show how causality can be used to penalise such lazy agents and improve their behaviours. By understanding how their local observations are causally related to the team reward, each agent in the team can adjust their individual credit based on whether they helped to cause the reward or not. We show empirically that using causality estimations in MARL improves not only the holistic performance of the team, but also the individual capabilities of each agent. We observe that the improvements are consistent in a set of different environments.

Recent deep learning frameworks draw strong research interest in application of ego-motion estimation as they demonstrate a superior result compared to geometric approaches. However, due to the lack of multimodal datasets, most of these studies primarily focused on single-sensor-based estimation. To overcome this challenge, we collect a unique multimodal dataset named LboroAV2 using multiple sensors, including camera, light detecting and ranging (LiDAR), ultrasound, e-compass and rotary encoder. We also propose an end-to-end deep learning architecture for fusion of RGB images and LiDAR laser scan data for odometry application. The proposed method contains a convolutional encoder, a compressed representation and a recurrent neural network. Besides feature extraction and outlier rejection, the convolutional encoder produces a compressed representation, which is used to visualise the network’s learning process and to pass useful sequential information. The recurrent neural network uses this compressed sequential data to learn the relationship between consecutive time steps. We use the Loughborough autonomous vehicle (LboroAV2) and the Karlsruhe Institute of Technology and Toyota Institute (KITTI) Visual Odometry (VO) datasets to experiment and evaluate our results. In addition to visualising the network’s learning process, our approach provides superior results compared to other similar methods. The code for the proposed architecture is released in GitHub and accessible publicly.

Recent deep learning frameworks draw a strong research interest in the application of ego-motion estimation as they demonstrate a superior result compared to geometric approaches. However, due to the lack of multimodal datasets, most of these studies primarily focused on a single sensor-based estimation. To overcome this challenge, we collect a unique multimodal dataset named LboroAV2, using multiple sensors including camera, Light Detecting And Ranging (LiDAR), ultrasound, e-compass and rotary encoder. We also propose an end-to-end deep learning architecture for fusion of RGB images and LiDAR laser scan data for odometry application. The proposed method contains a convolutional encoder, a compressed representation and a recurrent neural network. Besides feature extraction and outlier rejection, the convolutional encoder produces a compressed representation which is used to visualise the network's learning process and to pass useful sequential information. The recurrent neural network uses this compressed sequential data to learn the relation between consecutive time steps. We use the LboroAV2 and KITTI VO datasets to experiment and evaluate our results. In addition to visualising the network's learning process, our approach gives superior results compared to other similar methods. The code for the proposed architecture is released in GitHub and accessible publicly.