Related papers: AMPED: Adaptive Multi-objective Projection for bal…

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were…

Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks…

Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of…

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods primarily rely on self-exploration or a single off-policy teacher…

Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient…

Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based…

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples…

Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conflicts by sparsifying task vectors or promoting orthogonality…

Reinforcement Learning (RL), recognized as an efficient learning approach, has achieved remarkable success across multiple fields and applications, including gaming, robotics, and autonomous vehicles. Classical single-agent reinforcement…

In recent years, reinforcement learning (RL) has shown outstanding performance for locomotion control of highly articulated robotic systems. Such approaches typically involve tedious reward function tuning to achieve the desired motion…

Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied…

Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…

Model-based reinforcement learning (RL) is a sample-efficient way of learning complex behaviors by leveraging a learned single-step dynamics model to plan actions in imagination. However, planning every action for long-horizon tasks is not…

Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected…

Navigating urban intersections, especially when interacting with heterogeneous traffic participants, presents a formidable challenge for autonomous vehicles (AVs). In such environments, safety risks arise simultaneously from multiple…

Adaptive learning often diagnoses precisely yet intervenes weakly, yielding help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence…

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine learning, in many…

The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of…

Articulated object manipulation is a challenging task, requiring constrained motion and adaptive control to handle the unknown dynamics of the manipulated objects. While reinforcement learning (RL) has been widely employed to tackle various…