相关论文: Open-Ended Reinforcement Learning with Neural Rewa…

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these…

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

World models simulate dynamic environments, enabling agents to interact with diverse input modalities. Although recent advances have improved the visual quality and temporal consistency of video world models, their ability of accurately…

Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from…

Tactical decision making and strategic motion planning for autonomous highway driving are challenging due to the complication of predicting other road users' behaviors, diversity of environments, and complexity of the traffic interactions.…

Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties. Using rewards on an ordinal scale (ordinal rewards) is an alternative to numerical rewards that has…

Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learning yet even a tiny…

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Reinforcement learning (RL) is attracting attention as an effective way to solve sequential optimization problems that involve high dimensional state/action space and stochastic uncertainties. Many such problems involve constraints…

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only,…

Supervised learning, more specifically Convolutional Neural Networks (CNN), has surpassed human ability in some visual recognition tasks such as detection of traffic signs, faces and handwritten numbers. On the other hand, even…

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the…

End-to-end reinforcement learning techniques are among the most successful methods for robotic manipulation tasks. However, the training time required to find a good policy capable of solving complex tasks is prohibitively large. Therefore,…

Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimodal reward function. This assumption does not always hold…

Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…

Supervised deep convolutional neural networks (DCNNs) are currently one of the best computational models that can explain how the primate ventral visual stream solves object recognition. However, embodied cognition has not been considered…