Centralised training with decentralised execution is an important setting for cooperative
deep multi-agent reinforcement learning due to communication constraints during execution …

Role-based learning holds the promise of achieving scalable multi-agent learning by
decomposing complex tasks using roles. However, it is largely unclear how to efficiently …

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a
centralized action value function as a monotonic mixing of per-agent utilities. While this …

Reinforcement Learning in large action spaces is a challenging problem. This is especially
true for cooperative multi-agent reinforcement learning (MARL), which often requires …

Applying probabilistic models to reinforcement learning (RL) enables the uses of powerful
optimisation tools such as variational inference in RL. However, existing inference …

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but
its current application to robotics is currently hindered by high sample requirements. To …

Symmetry, a fundamental concept to understand our environment, often oversimplifies
reality from a mathematical perspective. Humans are a prime example, deviating from …

This paper proposes a new method to drastically speed up deep reinforcement learning
(deep RL) training for problems that have the property of state-action permissibility (SAP) …

This paper is concerned with deep reinforcement learning (deep RL) in continuous state and
action space. It proposes a new method that can drastically speed up RL training for …

Symmetry, a fundamental concept to understand our environment, often oversimplifies
reality from a mathematical perspective. Humans are a prime example, deviating from …