相关论文: Curious Replay for Model-based Adaptation

In the last decade, deep learning has achieved great success in machine learning tasks where the input data is represented with different levels of abstractions. Driven by the recent research in reinforcement learning using deep neural…

In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a large diversity of goals, aiming to discover what is…

Agents should avoid unsafe behaviour during both training and deployment. This typically requires a simulator and a procedural specification of unsafe behaviour. Unfortunately, a simulator is not always available, and procedurally…

Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…

Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…

What drives an agent to explore the world while also maintaining control over the environment? From a child at play to scientists in the lab, intelligent agents must balance curiosity (the drive to seek knowledge) with competence (the drive…

The experience replay mechanism allows agents to use the experiences multiple times. In prior works, the sampling probability of the transitions was adjusted according to their importance. Reassigning sampling probabilities for every…

Deep reinforcement learning (DRL) gives the promise that an agent learns good policy from high-dimensional information, whereas representation learning removes irrelevant and redundant information and retains pertinent information. In this…

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

As AI technology advances, research in playing text-based games with agents has becomeprogressively popular. In this paper, a novel approach to agent design and agent learning ispresented with the context of reinforcement learning. A model…

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning agents. The goal is to…

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human…

Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought…

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…

In reinforcement learning, Reverse Experience Replay (RER) is a recently proposed algorithm that attains better sample complexity than the classic experience replay method. RER requires the learning algorithm to update the parameters…

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to improve performance, uniform sampling by far remains the…

Real-world reinforcement learning applications are often hindered by delayed feedback from environments, which violates the Markov assumption and introduces significant challenges. Although numerous delay-compensating methods have been…