相关论文: Bridging the Imitation Gap by Adaptive Insubordina…

Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…

Inverse Reinforcement Learning addresses the problem of inferring an expert's reward function from demonstrations. However, in many applications, we not only have access to the expert's near-optimal behavior, but we also observe part of her…

Human gaze is known to be an intention-revealing signal in human demonstrations of tasks. In this work, we use gaze cues from human demonstrators to enhance the performance of agents trained via three popular imitation learning methods --…

Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many…

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict…

Transfer learning is an important new subfield of multiagent reinforcement learning that aims to help an agent learn about a problem by using knowledge that it has gained solving another problem, or by using knowledge that is communicated…

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm,…

Imitation learning is the process by which one agent tries to learn how to perform a certain task using information generated by another, often more-expert agent performing that same task. Conventionally, the imitator has access to both…

Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not trivial because the goal behind the gap is difficult to reach.…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function…

Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world…

This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue…

Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by…

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…

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

The i.i.d. assumption is a useful idealization that underpins many successful approaches to supervised machine learning. However, its violation can lead to models that learn to exploit spurious correlations in the training data, rendering…

Adversarial imitation learning (AIL) has become a popular alternative to supervised imitation learning that reduces the distribution shift suffered by the latter. However, AIL requires effective exploration during an online reinforcement…

State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal…