Search Results for author:
Found 48 papers, 12 papers with code
Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning
However, the relationship between specific exploration characteristics and effective transfer learning in deep RL has not been characterized.
Novelty Detection in Reinforcement Learning with World Models
We refer to the sudden change in visual properties or state transitions as novelties.
Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI
Utilizing two case studies in distinct domains, we empirically derive a framework that facilitates systematic charting of the sociotechnical gap by connecting AI guidelines in the context of XAI and elucidating how to use them to address the gap.
Neuro-Symbolic World Models for Adapting to Open World Novelty
Additionally, WorldCloner augments the policy learning process using imagination-based adaptation, where the world model simulates transitions of the post-novelty environment to help the policy adapt.
Neural Story Planning
Traditional symbolic planners plan a story from a goal state and guarantee logical causal plot coherence but rely on a library of hand-crafted actions with their preconditions and effects.
Seamful XAI: Operationalizing Seamful Design in Explainable AI
We found that the Seamful XAI design process helped users foresee AI harms, identify underlying reasons (seams), locate them in the AI's lifecycle, learn how to leverage seamful information to improve XAI and user agency.
Social Construction of XAI: Do We Need One Definition to Rule Them All?
There is a growing frustration amongst researchers and developers in Explainable AI (XAI) around the lack of consensus around what is meant by 'explainability'.
Experiential Explanations for Reinforcement Learning
However, RL agents discard the qualitative features of their training, making it difficult to recover user-understandable information for "why" an action is chosen.
The Algorithmic Imprint
When algorithmic harms emerge, a reasonable response is to stop using the algorithm to resolve concerns related to fairness, accountability, transparency, and ethics (FATE).
Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning
The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story.
Guiding Neural Story Generation with Reader Models
In this paper, we introduce Story generation with Reader Models (StoRM), a framework in which a reader model is used to reason about the story should progress.
Inherently Explainable Reinforcement Learning in Natural Language
We focus on the task of creating a reinforcement learning agent that is inherently explainable -- with the ability to produce immediate local explanations by thinking out loud while performing a task and analyzing entire trajectories post-hoc to produce causal explanations.
Situated Dialogue Learning through Procedural Environment Generation
We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums.
Explainability Pitfalls: Beyond Dark Patterns in Explainable AI
To make Explainable AI (XAI) systems trustworthy, understanding harmful effects is just as important as producing well-designed explanations.
The Who in XAI: How AI Background Shapes Perceptions of AI Explanations
Explainability of AI systems is critical for users to take informed actions.
Modeling Worlds in Text
We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives.
Learning Knowledge Graph-based World Models of Textual Environments
World models improve a learning agent's ability to efficiently operate in interactive and situated environments.
Detecting and Adapting to Novelty in Games
Open-world novelty occurs when the rules of an environment can change abruptly, such as when a game player encounters "house rules".
Telling Stories through Multi-User Dialogue by Modeling Character Relations
This paper explores character-driven story continuation, in which the story emerges through characters' first- and second-person narration as well as dialogue -- requiring models to select language that is consistent with a character's persona and their relationships with other characters while following and advancing the story.
LEx: A Framework for Operationalising Layers of Machine Learning Explanations
Several social factors impact how people respond to AI explanations used to justify AI decisions affecting them personally.
Situated Language Learning via Interactive Narratives
This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal.
Expanding Explainability: Towards Social Transparency in AI systems
We suggested constitutive design elements of ST and developed a conceptual framework to unpack ST's effect and implications at the technical, decision-making, and organizational level.
Playing Text-Based Games with Common Sense
We test our technique in the 9to05 game, which is an extreme version of a text based game that requires numerous interactions with common, everyday objects in common, everyday scenarios.
Automated Storytelling via Causal, Commonsense Plot Ordering
In this work, we introduce the concept of soft causal relations as causal relations inferred from commonsense reasoning.
How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards.
How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.
Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach
In this paper, we introduce Human-centered Explainable AI (HCXAI) as an approach that puts the human at the center of technology design.
Bringing Stories Alive: Generating Interactive Fiction Worlds
This knowledge graph is then automatically completed utilizing thematic knowledge and used to guide a neural language generation model that fleshes out the rest of the world.
Integrating Automated Play in Level Co-Creation
In level co-creation an AI and human work together to create a video game level.
Toward Automated Quest Generation in Text-Adventure Games
Text-adventure games are typically structured as puzzles or quests wherein the player must execute certain actions in a certain order to succeed.
Story Realization: Expanding Plot Events into Sentences
Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries.
Ranked #1 on
Event Expansion
on Scifi TV Shows
Automated Let's Play Commentary
Let's Plays of video games represent a relatively unexplored area for experimental AI in games.
Transfer in Deep Reinforcement Learning using Knowledge Graphs
Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language.
Automatic Game Design via Mechanic Generation
We use a constraint solver to generate mechanics subject to design requirements on the form of those mechanics---what they do in the game.
Automatic Playtesting for Game Parameter Tuning via Active Learning
Through a case study on a shoot-`em-up game we demonstrate the efficacy of active learning to reduce the amount of playtesting needed to choose the optimal set of game parameters for two classes of (formal) design objectives.
Monte-Carlo Tree Search for Simulation-based Strategy Analysis
Using these case studies, we show how using simulated agents to model humans of varying skill levels allows us to extract metrics to describe game balance (in the case of Scrabble) and highlight potential design flaws (in the case of Cardonomicon).
Human-Centered Artificial Intelligence and Machine Learning
Humans are increasingly coming into contact with artificial intelligence and machine learning systems.
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language.
Controllable Neural Story Plot Generation via Reward Shaping
Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story.
Creative Invention Benchmark
In this paper we present the Creative Invention Benchmark (CrIB), a 2000-problem benchmark for evaluating a particular facet of computational creativity.
Combinets: Creativity via Recombination of Neural Networks
One of the defining characteristics of human creativity is the ability to make conceptual leaps, creating something surprising from typical knowledge.
Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback.
Guiding Reinforcement Learning Exploration Using Natural Language
We then use this learned model to guide agent exploration using a modified version of policy shaping to make it more effective at learning in unseen environments.
Event Representations for Automated Story Generation with Deep Neural Nets
We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence).
Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch.
Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.
Computational Narrative Intelligence: A Human-Centered Goal for Artificial Intelligence
Narrative intelligence is the ability to craft, tell, understand, and respond affectively to stories.
The Lovelace 2.0 Test of Artificial Creativity and Intelligence
Observing that the creation of certain types of artistic artifacts necessitate intelligence, we present the Lovelace 2. 0 Test of creativity as an alternative to the Turing Test as a means of determining whether an agent is intelligent.
