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

10/08/2020
by   Keerthiram Murugesan, et al.
49

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.

READ FULL TEXT
05/02/2020

Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge

In this paper, we consider the recent trend of evaluating progress on re...
07/17/2020

WordCraft: An Environment for Benchmarking Commonsense Agents

The ability to quickly solve a wide range of real-world tasks requires a...
01/28/2022

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

Enabling reinforcement learning (RL) agents to leverage a knowledge base...
10/22/2020

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

We study reinforcement learning (RL) for text-based games, which are int...
04/28/2020

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

We propose an unsupervised approach for sarcasm generation based on a no...
10/16/2021

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

Text-based games (TBG) have emerged as promising environments for drivin...
09/21/2022

Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

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

Code Repositories

commonsense-rl

Knowledge-Aware RL agents with Commonsense Reasoning


view repo