Chongjie Zhang

• PostDoc Position at Massachusetts Institute of Technology

Coordinating multi-agent reinforcement learning provides a promising approach to scaling learning in large cooperative multi-agent systems. It allows agents to learn local decision policies based on their local observations and rewards, and, meanwhile, coordinates agents' learning processes to ensure the global learning performance. One key questio...

Coordinated multi-agent reinforcement learning (MARL) provides a promising approach to scaling learning in large cooperative multi-agent systems. Distributed constraint optimization (DCOP) techniques have been used to coordinate action selection among agents during both the learning phase and the policy execution phase (if learning is off-line) to...

We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, co...

In many multi-agent applications such as distributed sensor nets, a network of agents act collaboratively under uncertainty and local interactions. Networked Distributed POMDP (ND-POMDP) provides a framework to model such cooperative multi-agent decision making. Existing work on ND-POMDPs has focused on offline techniques that require accurate mode...

In many multi-agent applications such as distributed sensor nets, a network of agents act collaboratively under uncertainty and local interactions. Networked Distributed POMDP (ND-POMDP) provides a framework to model such cooperative multi-agent decision making. Existing work on ND-POMDPs has focused on offline techniques that require accurate mode...

Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting the basic gradient ascent approach with policy prediction. We prove that this augmentation results in a stronger notion of convergence than the basic gradient ascent, that i...

Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting the basic gradient ascent approach with policy prediction. We prove that this augmentation results in a stronger notion of convergence than the basic gradient ascent, that i...

Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous work has shown that hierarchically organizational control is an effective way of coordinating DRL to improve its speed, quality, and likelihood of convergence. In this pap...

Resource allocation in computing clusters is traditionally centralized, which limits the cluster scale. Effective resource allocation in a network of computing clusters may enable building larger computing infrastructures. We consider this problem as a novel application for multiagent learning (MAL). We propose a MAL algorithm and apply it for opti...

Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large- scale systems. In this work, we develop an organization-based control framework to speed up the convergence of MARL algo- rithms in a network of agents. Our framework defines a multi-level organizational structure for automate...

Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algorithms in a network of agents. The framework defines an organizational structure for automated supervision and a communicat...

SUMMARY In this paper we discuss two of the major Grid portal solutions, the Open Grid Computing Environments Collaboratory (OGCE) and GridPortlets, both of which provide basic tools that portal developers can use to interact with Grid middleware when designing their own custom or application-specific Grid portals. We investigate and compare what e...

SUMMARY We describe the background, architecture and implementation of a user portal for the SCOOP coastal ocean observing and modeling community. SCOOP is engaged in real time prediction of severe weather events, including tropical storms and hurricanes, and provides operational information including wind, storm surge and resulting inundation, whi...

Reservoir simulations are commonly used to predict the performance of oil and gas reservoirs, taking into account a myriad of uncertainties in the geophysical structure of the reservoir as well as operational factors such as well location. Designed reservoir study provides a robust tool to quantify the impact of uncertainties in model input variabl...

The storing of data and configuration files related to scientific experiments is vital if those experiments are to remain reproducible, or if the data is to be shared easily. The prescence of historical (observed) data is also important in order to assist in model evaluation and development. This paper describes the design and implementation proces...

Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algo-rithms in a network of agents. Our framework defines a multi-level organizational structure for automated supervision and...

Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algo-rithms in a network of agents. Our framework defines a multi-level organizational structure for automated supervision and...

Resource management in clusters traditionally uses centralized approaches, which restricts the cluster scale. To expand this limit, we develop a multi-agent approach to sharing resources across clusters in a decentralized manner. We or-ganize shared clustered into an overlay network and formulate resource sharing in such a network as a distributed...