Related papers: AlphaStar Unplugged: Large-Scale Offline Reinforce…

We present a different view for AlphaStar (AS), the program achieving Grand-Master level in the game StarCraft II. It is considered big progress for AI research. However, in this paper, we present problems with the AS, some of which are the…

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…

Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy…

Offline reinforcement learning is used to train policies in scenarios where real-time access to the environment is expensive or impossible. As a natural consequence of these harsh conditions, an agent may lack the resources to fully observe…

Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled…

Macro-management is an important problem in StarCraft, which has been studied for a long time. Various datasets together with assorted methods have been proposed in the last few years. But these datasets have some defects for boosting the…

Real-time strategy (RTS) games make heavy use of artificial intelligence (AI), especially in the design of computerized opponents. Because of the computational complexity involved in managing all aspects of these games, many AI opponents…

Offline reinforcement learning has emerged as a promising technology by enhancing its practicality through the use of pre-collected large datasets. Despite its practical benefits, most algorithm development research in offline reinforcement…

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and…

Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such…

In recent years, researchers have achieved great success in applying Deep Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games, creating strong autonomous agents that could defeat professional players in StarCraft~II.…

In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with unknown…

Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a…

Learning tabula rasa, that is without any prior knowledge, is the prevalent workflow in reinforcement learning (RL) research. However, RL systems, when applied to large-scale settings, rarely operate tabula rasa. Such large-scale systems…

With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems. Despite its reputation, data inefficiency caused by its trial and error learning mechanism makes…

Batch reinforcement learning (BRL) is an emerging research area in the RL community. It learns exclusively from static datasets (i.e. replay buffers) without interaction with the environment. In the offline settings, existing replay…

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

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…

Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previously collected by safe policies. While previous work…

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…