Related papers: Negative Update Intervals in Deep Multi-Agent Rein…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by learning directly from image input. A deep neural network is used as a function approximator and requires no specific state information.…
Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most algorithms, based on temporal differences, replace the true value of a transiting state by their current estimate of this value. Yet, another estimate could be leveraged…
Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The…
In this paper, we study the problem of robust cooperative multi-agent reinforcement learning (RL) where a large number of cooperative agents with distributed information aim to learn policies in the presence of \emph{stochastic} and…
Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To…
In heterogeneous networks (HetNets), the overlap of small cells and the macro cell causes severe cross-tier interference. Although there exist some approaches to address this problem, they usually require global channel state information,…
In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The…
In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning…
Multi-step methods such as Retrace($\lambda$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations…
Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods…
Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…
Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…
We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs…
In multi-agent informative path planning (MAIPP), agents must collectively construct a global belief map of an underlying distribution of interest (e.g., gas concentration, light intensity, or pollution levels) over a given domain, based on…
Mean field games (MFGs) have emerged as a powerful framework for modeling interactions in large-scale multi-agent systems. Despite recent advancements in reinforcement learning (RL) for MFGs, existing methods are typically limited to finite…
Imitation learning traditionally requires complete state-action demonstrations from optimal or near-optimal experts. These requirements severely limit practical applicability, as many real-world scenarios provide only state observations…
Autonomous Intersection Management (AIM) provides a signal-free intersection scheduling paradigm for Connected Autonomous Vehicles (CAVs). Distributed learning method has emerged as an attractive branch of AIM research. Compared with…
Adaptive Mixed-Criticality (AMC) is a fixed-priority preemptive scheduling algorithm for mixed-criticality hard real-time systems. It dominates many other scheduling algorithms for mixed-criticality systems, but does so at the cost of…
When a reinforcement learning (RL) method has to decide between several optional policies by solely looking at the received reward, it has to implicitly optimize a Multi-Armed-Bandit (MAB) problem. This arises the question: are current RL…
We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance,…