Recent studies show that deep reinforcement learning (DRL) agents tend t...
Reinforcement Learning (RL) environments can produce training data with
...
There is a lack of standard benchmarks for Multi-Agent Reinforcement Lea...
One of the key challenges of Reinforcement Learning (RL) is the ability ...
MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that...
We present a novel framework to generate causal explanations for the
dec...
Training a team to complete a complex task via multi-agent reinforcement...
Cooperative multi-agent reinforcement learning (MARL) requires agents to...
This project leverages advances in multi-agent reinforcement learning (M...
Reasoning with occluded traffic agents is a significant open challenge f...
Accurate prediction is important for operating an autonomous vehicle in
...
Open ad hoc teamwork is the problem of training a single agent to effici...
Equilibrium selection in multi-agent games refers to the problem of sele...
The development of autonomous agents which can interact with other agent...
Achieving safe and robust autonomy is the key bottleneck on the path tow...
Ad hoc teamwork (AHT) is the problem of creating an agent that must
coll...
We propose the novel few-shot teamwork (FST) problem, where skilled agen...
While research in ad hoc teamwork has great potential for solving real-w...
In real-world robotics applications, Reinforcement Learning (RL) agents ...
Successful deployment of multi-agent reinforcement learning often requir...
When used in autonomous driving, goal recognition allows the future beha...
Learning control from pixels is difficult for reinforcement learning (RL...
Inscrutable AI systems are difficult to trust, especially if they operat...
We present MIDGARD, an open source simulation platform for autonomous ro...
Motion prediction of road users in traffic scenes is critical for autono...
Ad hoc teamwork is the well-established research problem of designing ag...
This paper considers how to complement offline reinforcement learning (R...
Deep reinforcement learning (RL) agents that exist in high-dimensional s...
Recognising the goals or intentions of observed vehicles is a key step
t...
Intrinsic rewards are commonly applied to improve exploration in
reinfor...
It is useful for autonomous vehicles to have the ability to infer the go...
Sharing parameters in multi-agent deep reinforcement learning has played...
Current methods for authentication based on public-key cryptography are
...
Ad hoc teamwork is the challenging problem of designing an autonomous ag...
Modelling the behaviours of other agents (opponents) is essential for
un...
Multi-agent deep reinforcement learning (MARL) suffers from a lack of
co...
Exploration in multi-agent reinforcement learning is a challenging probl...
The ability to predict the intentions and driving trajectories of other
...
Lessons learned from the increasing diversity of road trial deployments ...
Multi-agent systems exhibit complex behaviors that emanate from the
inte...
Generative Adversarial Networks (GANs) are a type of Generative Models, ...
Past research has studied two approaches to utilise predefined policy se...
This paper is concerned with evaluating different multiagent learning (M...
While many multiagent algorithms are designed for homogeneous systems (i...
Many multiagent applications require an agent to learn quickly how to
in...
Dynamic Bayesian networks (DBNs) are a general model for stochastic proc...
The key for effective interaction in many multiagent applications is to
...
Agents can achieve effective interaction with previously unknown other a...
Recent developments in deep reinforcement learning are concerned with
cr...
Methods for learning optimal policies in autonomous agents often assume ...