In this paper we present the Creative Invention Benchmark (CrIB), a 2000-problem benchmark for evaluating a particular facet of computational creativity. Specifically, we address combinational p-creativity, the creativity at play when someone combines existing knowledge to achieve a solution novel to that individual. We present generation strategies for the five problem categories of the benchmark and a set of initial baselines.
We introduce AI rationalization, an approach for generating explanations of autonomous system behavior as if a human had performed the behavior. We describe a rationalization technique that uses neural machine translation to translate internal state-action representations of an autonomous agent into natural language. We evaluate our technique in the Frogger game environment, training an autonomous game playing agent to rationalize its action choices using natural language. A natural language training corpus is collected from human players thinking out loud as they play the game. We motivate the use of rationalization as an approach to explanation generation and show the results of two experiments evaluating the effectiveness of rationalization. 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.
In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action information. 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. We evaluate this technique using the popular arcade game, Frogger, under ideal and non-ideal conditions. This evaluation shows that our modified policy shaping algorithm improves over a Q-learning agent as well as a baseline version of policy shaping.
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. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent's environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation using a synthetic oracle, we show that our technique improves the training speed and overall performance of deep reinforcement learning in navigating three-dimensional environments using Minecraft. We further show that our technique is robust to highly innacurate human feedback and can also operate when no human feedback is given.
Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. 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). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language.
Robots and autonomous systems that operate around humans will likely always rely on kill switches that stop their execution and allow them to be remote-controlled for the safety of humans or to prevent damage to the system. It is theoretically possible for an autonomous system with sufficient sensor and effector capability and using reinforcement learning to learn that the kill switch deprives it of long-term reward and learn to act to disable the switch or otherwise prevent a human operator from using the switch. This is referred to as the big red button problem. We present a technique which prevents a reinforcement learning agent from learning to disable the big red button. Our technique interrupts the agent or robot by placing it in a virtual simulation where it continues to receive reward. We illustrate our technique in a simple grid world environment.
Narrative intelligence is the ability to craft, tell, understand, and respond affectively to stories. We argue that instilling artificial intelligences with computational narrative intelligence affords a number of applications beneficial to humans. We lay out some of the machine learning challenges necessary to solve to achieve computational narrative intelligence. Finally, we argue that computational narrative is a practical step towards machine enculturation, the teaching of sociocultural values to machines.
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. The Lovelace 2.0 Test builds off prior tests of creativity and additionally provides a means of directly comparing the relative intelligence of different agents.