Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

by   Keerthiram Murugesan, et al.

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agents with commonsense knowledge. Such knowledge would allow agents to efficiently act in the world by pruning out implausible actions, and to perform look-ahead planning to determine how current actions might affect future world states. We design a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances. We also introduce several baseline RL agents which track the sequential context and dynamically retrieve the relevant commonsense knowledge from ConceptNet. We show that agents which incorporate commonsense knowledge in TWC perform better, while acting more efficiently. We conduct user-studies to estimate human performance on TWC and show that there is ample room for future improvement.


Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge

In this paper, we consider the recent trend of evaluating progress on re...

WordCraft: An Environment for Benchmarking Commonsense Agents

The ability to quickly solve a wide range of real-world tasks requires a...

Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods

Enabling reinforcement learning (RL) agents to leverage a knowledge base...

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

We study reinforcement learning (RL) for text-based games, which are int...

R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

We propose an unsupervised approach for sarcasm generation based on a no...

Case-based Reasoning for Better Generalization in Text-Adventure Games

Text-based games (TBG) have emerged as promising environments for drivin...

Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

Modern power systems are experiencing a variety of challenges driven by ...

Code Repositories


Knowledge-Aware RL agents with Commonsense Reasoning

view repo