Related papers: Relational Object-Centric Actor-Critic

We focus on a simulation-based optimization problem of choosing the best design from the feasible space. Although the simulation model can be queried with finite samples, its internal processing rule cannot be utilized in the optimization…

In this paper, we consider the problem of actor-critic reinforcement learning. Firstly, we extend the actor-critic architecture to actor-critic-N architecture by introducing more critics beyond rewards. Secondly, we combine the reward-based…

Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a grounded abstract representation and identify the…

As learning-based robotic controllers are typically trained offline and deployed with fixed parameters, their ability to cope with unforeseen changes during operation is limited. Biologically inspired, this work presents a framework for…

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions. Inspired by human perception, object-centric world models capture scene dynamics using object-level representations, which can…

Autonomous intelligent agents must bridge computational challenges at disparate levels of abstraction, from the low-level spaces of sensory input and motor commands to the high-level domain of abstract reasoning and planning. A key question…

Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance. Meanwhile, their inherent sample efficiency warrants utility for…

We focus on the task of language-conditioned object placement, in which a robot should generate placements that satisfy all the spatial relational constraints in language instructions. Previous works based on rule-based language parsing or…

We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors…

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…

Reinforcement learning (RL) and causal modelling naturally complement each other. The goal of causal modelling is to predict the effects of interventions in an environment, while the goal of reinforcement learning is to select interventions…

Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the…

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…

Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class). Common to all of these approaches is the assumption that…

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether…

Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical…

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to…

Visual representations are central to the learning and generalization capabilities of robotic manipulation policies. While existing methods rely on global or dense features, such representations often entangle task-relevant and irrelevant…