Related papers: CEIP: Combining Explicit and Implicit Priors for R…
We introduce a learning method called ``gradient-based reinforcement planning'' (GREP). Unlike traditional DP methods that improve their policy backwards in time, GREP is a gradient-based method that plans ahead and improves its policy…
Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data…
Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…
Robust real-world learning should benefit from both demonstrations and interactions with the environment. Current approaches to learning from demonstration and reward perform supervised learning on expert demonstration data and use…
Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…
Humans often think of complex tasks as combinations of simpler subtasks in order to learn those complex tasks more efficiently. For example, a backflip could be considered a combination of four subskills: jumping, tucking knees, rolling…
The motivation of this study is to leverage recent breakthroughs in artificial intelligence research to unlock novel solutions to important scientific problems encountered in computational science. To address the human intelligence…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…
It is important to collect credible training samples $(x,y)$ for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distribution $p(x)$, though theoretically viable, is challenging in…
Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task. But an initialization contains…
Agents that interact with other agents often do not know a priori what the other agents' strategies are, but have to maximise their own online return while interacting with and learning about others. The optimal adaptive behaviour under…
Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is…
Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…
When autonomous vehicles are deployed on public roads, they will encounter countless and diverse driving situations. Many manually designed driving policies are difficult to scale to the real world. Fortunately, reinforcement learning has…
We present ImplicitSLIM, a novel unsupervised learning approach for sparse high-dimensional data, with applications to collaborative filtering. Sparse linear methods (SLIM) and their variations show outstanding performance, but they are…
A desirable property of learning systems is to be both effective and interpretable. Towards this goal, recent models have been proposed that first generate an extractive explanation from the input text and then generate a prediction on just…
Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pretraining (CLIP),…
Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…
While large scale pre-training has achieved great achievements in bridging the gap between vision and language, it still faces several challenges. First, the cost for pre-training is expensive. Second, there is no efficient way to handle…
Constant envelope (CE) precoding design is of great interest for massive multiuser multi-input multi-output systems because it can significantly reduce hardware cost and power consumption. However, existing CE precoding algorithms are…