Related papers: Studying the Interplay Between the Actor and Criti…

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

Goal Recognition aims to infer an agent's goal from a sequence of observations. Existing approaches often rely on manually engineered domains and discrete representations. Deep Recognition using Actor-Critic Optimization (DRACO) is a novel…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the…

Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issues. In this paper, we address these challenges by providing…

To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of…

Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL)…

We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master…

Most approaches to visual scene analysis have emphasised parallel processing of the image elements. However, one area in which the sequential nature of vision is apparent, is that of segmenting multiple, potentially similar and partially…

Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for…

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…

To make efficient use of limited spectral resources, we in this work propose a deep actor-critic reinforcement learning based framework for dynamic multichannel access. We consider both a single-user case and a scenario in which multiple…

Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper,…

We propose a fully distributed actor-critic architecture, named Diff-DAC, with application to multitask reinforcement learning (MRL). During the learning process, agents communicate their value and policy parameters to their neighbours,…

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong…

In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive…

Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences.…