Related papers: Prosocial or Selfish? Agents with different behavi…
Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…
This paper investigates how deep multi-agent reinforcement learning can enable the scalable and privacy-preserving coordination of residential energy flexibility. The coordination of distributed resources such as electric vehicles and…
We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…
Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…
Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's…
The demand for more transparency of decision-making processes of deep reinforcement learning agents is greater than ever, due to their increased use in safety critical and ethically challenging domains such as autonomous driving. In this…
From social networks to traffic routing, artificial learning agents are playing a central role in modern institutions. We must therefore understand how to leverage these systems to foster outcomes and behaviors that align with our own…
Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…
Mixed incentives among a population with multiagent teams has been shown to have advantages over a fully cooperative system; however, discovering the best mixture of incentives or team structure is a difficult and dynamic problem. We…
In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While…
Robot assistants for older adults and people with disabilities need to interact with their users in collaborative tasks. The core component of these systems is an interaction manager whose job is to observe and assess the task, and infer…
We present a method for using previously-trained 'teacher' agents to kickstart the training of a new 'student' agent. To this end, we leverage ideas from policy distillation and population based training. Our method places no constraints on…
In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent…
Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a…
Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated using imitation learning, where the agent learns to imitate…
Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training…
Evaluating deep multiagent reinforcement learning (MARL) algorithms is complicated by stochasticity in training and sensitivity of agent performance to the behavior of other agents. We propose a meta-game evaluation framework for deep MARL,…
Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these…
There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train agents to collaborate…