相关论文: Human-level Atari 200x faster

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…

Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations being limited to in-distribution environments and non-unified…

Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each…

Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the…

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent…

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…

As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks that assess specific capabilities of the agents can be…

Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially…

Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely…

To obtain higher sample efficiency and superior final performance simultaneously has been one of the major challenges for deep reinforcement learning (DRL). Previous work could handle one of these challenges but typically failed to address…

Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to…

Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggle to handle novel…

Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in…

In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games. However, the current manifestation of DRL is…

Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go, where a…

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning…

Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other,…

The rapid pace of recent research in AI has been driven in part by the presence of fast and challenging simulation environments. These environments often take the form of games; with tasks ranging from simple board games, to competitive…

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…