Related papers: Learning From Failures: Efficient Reinforcement Le…
Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…
Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is…
Large language models (LLMs) struggle with maintaining coherence in extended conversations spanning hundreds of turns, despite performing well within their context windows. This paper introduces HEMA (Hippocampus-Inspired Extended Memory…
Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online…
In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get…
In recent years, the development of Artificial Intelligence (AI) has shown tremendous potential in diverse areas. Among them, reinforcement learning (RL) has proven to be an effective solution for learning intelligent control strategies. As…
Recent works use a neuro-symbolic framework for general manipulation policies. The advantage of this framework is that -- by applying off-the-shelf vision and language models -- the robot can break complex tasks down into semantic subtasks.…
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e.,…
As reinforcement learning for humanoid robots evolves from single-task to multi-skill paradigms, efficiently expanding new skills while avoiding catastrophic forgetting has become a key challenge in embodied intelligence. Existing…
The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice. When demonstrations are generated by sub-optimal policies or…
Catastrophic forgetting in continual learning is a common destructive phenomenon in gradient-based neural networks that learn sequential tasks, and it is much different from forgetting in humans, who can learn and accumulate knowledge…
The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…
Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where…
Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling…
While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…
In this paper, we address the issue of increasing the performance of reinforcement learning (RL) solutions for autonomous racing cars when navigating under conditions where practical vehicle modelling errors (commonly known as \emph{model…
Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…
This paper combines episodic learning and control barrier functions in the setting of bipedal locomotion. The safety guarantees that control barrier functions provide are only valid with perfect model knowledge; however, this assumption…