Related papers: Learning From Failures: Efficient Reinforcement Le…
Learning from human demonstrations can facilitate automation but is risky because the execution of the learned policy might lead to collisions and other failures. Adding explicit constraints to avoid unsafe states is generally not possible…
Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…
Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…
Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL…
Reinforcement learning-based (RL-based) energy management strategy (EMS) is considered a promising solution for the energy management of electric vehicles with multiple power sources. It has been shown to outperform conventional methods in…
Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…
This work introduces a robot navigation controller that combines event cameras and other sensors with reinforcement learning to enable real-time human-centered navigation and obstacle avoidance. Unlike conventional image-based controllers,…
Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a…
Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…
The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the…
Reinforcement Learning (RL) is an emerging approach to control many dynamical systems for which classical control approaches are not applicable or insufficient. However, the resultant policies may not generalize to variations in the…
Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…
Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…
Reinforcement learning (RL)-based driver assistance systems seek to improve fuel consumption via continual improvement of powertrain control actions considering experiential data from the field. However, the need to explore diverse…
Long-horizon multimodal agents depend on external memory; however, similarity-based retrieval often surfaces stale, low-credibility, or conflicting items, which can trigger overconfident errors. We propose Multimodal Memory Agent (MMA),…
In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and…
Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without…
Efficient navigation in dynamic environments is crucial for autonomous robots interacting with moving agents and static obstacles. We present a novel deep reinforcement learning approach that improves robot navigation and interaction with…
Skill effect models for long-horizon manipulation tasks are prone to failures in conditions not covered by training data distributions. Therefore, enabling robots to reason about and learn from failures is necessary. We investigate the…
Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…