TextWorld: A Learning Environment for Text-based Games

Côté, Marc-Alexandre; Kádár, Ákos; Yuan, Xingdi; Kybartas, Ben; Barnes, Tavian; Fine, Emery; Moore, James W.; Yu, Tao, Ruo; Hausknecht, Matthew; Asri, Layla El; Adada, Mahmoud; Tay, Wendy; Trischler, Adam

doi:10.48550/arxiv.1806.11532

Cited by 12 publications

(26 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TextWorld enables interactive playthrough of text-based games and, unlike other text-based environments such as TextPlayer 14 and PyFiction 15 , enables users to handcraft games or to construct games automatically. The TextWorld logic engine automatically builds game worlds, populates them with objects and obstacles, and generates quests that define a goal state and how to reach it [18]. TextWorld requires Python 3 and currently only supports Linux and macOS systems.…”

Section: Methodsmentioning

confidence: 99%

“…TextWorld requires Python 3 and currently only supports Linux and macOS systems. The code and documentation are available publicly 16 and the learning environment is described in full detail in Section 3 of [18], including descriptions of the two main components of the Python framework: a game generator and a game engine. To interact with TextWorld, the framework provides a simple application programming interface (API) which is inspired by OpenAI Gym.…”

Section: Methodsmentioning

confidence: 99%

“…Since the interpreter in parserbased games can accept any sequence of characters (of any length), but only a fraction thereof is recognised, the resulting action space is very large. Therefore, two simplifying assumptions are made in [18]: the commands are sequences of at most L words taken from a fixed vocabulary V and the commands have to follow a specific structure: a verb, a noun phrase and an adverb phrase. The action space of the agent is therefore the set of all permissible commands from the fixed vocabulary V followed by a certain special token ("enter") that signifies the end of the command.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, researchers from the Microsoft Research Montreal Lab released an open source project called TextWorld [18], which attempts to train reinforcement learning agents using text-based games.…”

Section: Microsoft Textworldmentioning

confidence: 99%

“…This paper provides a survey of the most important and most recent contributions to benchmarking for RL. These are OpenAI Gym [16], the Arcade Learning Environment [12], a continuous control benchmark rllab [13], RoboCup Keepaway soccer [17] and Microsoft TextWorld [18]. When solving RL problems, there are many challenges that need to be overcome, such as the fundamental trade-off problem between exploration and exploitation, partial observability of the environment, delayed rewards, enormous state spaces and so on.…”

mentioning

confidence: 99%

See 4 more Smart Citations

A survey of benchmarking frameworks for reinforcement learning

Stapelberg,

Malan

2020

Preprint

View full text Add to dashboard Cite

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems using reinforcement learning, there are various difficult challenges to overcome.To ensure progress in the field, benchmarks are important for testing new algorithms and comparing with other approaches. The reproducibility of results for fair comparison is therefore vital in ensuring that improvements are accurately judged. This paper provides an overview of different contributions to reinforcement learning benchmarking and discusses how they can assist researchers to address the challenges facing reinforcement learning. The contributions discussed are the most used and recent in the literature. The paper discusses the contributions in terms of implementation, tasks and provided algorithm implementations with benchmarks.The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner. Additionally, this survey acts as an overview for researchers not familiar with the different tasks that can be used to develop and test new reinforcement learning algorithms.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Microsoft Textworldmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

A survey of benchmarking frameworks for reinforcement learning

Stapelberg,

Malan

2020

Preprint

View full text Add to dashboard Cite

show abstract

Deep Learning for Video Game Playing

et al. 2020

View full text Add to dashboard Cite

In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games. We analyze the unique requirements that different game genres pose to a deep learning system and highlight important open challenges in the context of applying these machine learning methods to video games, such as general game playing, dealing with extremely large decision spaces and sparse rewards.

show abstract

Flow: A Modular Learning Framework for Mixed Autonomy Traffic

et al. 2022

View full text Add to dashboard Cite

The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, due to numerous technical, political, and human factors challenges, new methodologies are needed to design vehicles and transportation systems for these positive outcomes. This article tackles important technical challenges arising from the partial adoption of autonomy (hence termed mixed autonomy, to involve both AVs and human-driven vehicles): partial control, partial observation, complex multi-vehicle interactions, and the sheer variety of traffic settings represented by real-world networks. To enable the study of the full diversity of traffic settings, we first propose to decompose traffic control tasks into modules, which may be configured and composed to create new control tasks of interest. These modules include salient aspects of traffic control tasks: networks, actors, control laws, metrics, initialization, and additional dynamics. Second, we study the potential of modelfree deep Reinforcement Learning (RL) methods to address the complexity of traffic dynamics. The resulting modular learning framework is called Flow. Using Flow, we create and study a variety of mixed-autonomy settings, including single-lane, multilane, and intersection traffic. In all cases, the learned control law exceeds human driving performance (measured by systemlevel velocity) by at least 40% with only 5-10% adoption of AVs. In the case of partially-observed single-lane traffic, we show that a low-parameter neural network control law can eliminate commonly observed stop-and-go traffic. In particular, the control laws surpass all known model-based controllers, achieving nearoptimal performance across a wide spectrum of vehicle densities (even with a memoryless control law) and generalizing to out-ofdistribution vehicle densities.

show abstract

TextWorld: A Learning Environment for Text-based Games

Cited by 12 publications

References 0 publications

A survey of benchmarking frameworks for reinforcement learning

A survey of benchmarking frameworks for reinforcement learning

Deep Learning for Video Game Playing

Flow: A Modular Learning Framework for Mixed Autonomy Traffic

Contact Info

Product

Resources

About