Related papers: Katakomba: Tools and Benchmarks for Data-Driven Ne…
Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…
Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for…
While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data. By testing increasingly complex RL algorithms on…
An exciting and promising frontier for Deep Reinforcement Learning (DRL) is its application to real-world robotic systems. While modern DRL approaches achieved remarkable successes in many robotic scenarios (including mobile robotics,…
Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…
Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves…
In many reinforcement learning (RL) applications one cannot easily let the agent act in the world; this is true for autonomous vehicles, healthcare applications, and even some recommender systems, to name a few examples. Offline RL provides…
Offline multi-agent reinforcement learning (MARL) is an exciting direction of research that uses static datasets to find optimal control policies for multi-agent systems. Though the field is by definition data-driven, efforts have thus far…
The digital transformation is pushing the existing network technologies towards new horizons, enabling new applications (e.g., vehicular networks). As a result, the networking community has seen a noticeable increase in the requirements of…
The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development of models. The real-world offline RL dataset is often…
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will…
Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we…
Data processing and analytics are fundamental and pervasive. Algorithms play a vital role in data processing and analytics where many algorithm designs have incorporated heuristics and general rules from human knowledge and experience to…
As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which,…
Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches…
Q-learning methods represent a commonly used class of algorithms in reinforcement learning: they are generally efficient and simple, and can be combined readily with function approximators for deep reinforcement learning (RL). However, the…
Reinforcement Learning (RL) has achieved tremendous success in many complex decision-making tasks. However, safety concerns are raised during deploying RL in real-world applications, leading to a growing demand for safe RL algorithms, such…
Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…
Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving…