csAI

Why Couldn't You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice. (arXiv:1903.08218v1 [cs.AI])

[ad_1] Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans. While there has been a lot of research on generating explanations of solutions...

Read more
Aesthetics of Neural Network Art. (arXiv:1903.05696v1 [cs.AI])

[ad_1] This paper proposes a way to understand neural network artworks as juxtapositions of natural image cues. It is hypothesized that images with unusual combinations of realistic visual cues are...

Read more
Learning Self-Game-Play Agents for Combinatorial Optimization Problems. (arXiv:1903.03674v1 [cs.AI])

[ad_1] Recent progress in reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and...

Read more
ENIGMA-NG: Efficient Neural and Gradient-Boosted Inference Guidance for E. (arXiv:1903.03182v1 [cs.AI])

[ad_1] We describe an efficient implementation of clause guidance in saturation-based automated theorem provers extending the ENIGMA approach. Unlike in the first ENIGMA implementation where fast linear classifier is trained...

Read more
Can Sophisticated Dispatching Strategy Acquired by Reinforcement Learning? – A Case Study in Dynamic Courier Dispatching System. (arXiv:1903.02716v1 [cs.AI])

[ad_1] In this paper, we study a courier dispatching problem (CDP) raised from an online pickup-service platform of Alibaba. The CDP aims to assign a set of couriers to serve...

Read more
Concurrent Meta Reinforcement Learning. (arXiv:1903.02710v1 [cs.AI])

[ad_1] State-of-the-art meta reinforcement learning algorithms typically assume the setting of a single agent interacting with its environment in a sequential manner. A negative side-effect of this sequential execution paradigm...

Read more
Discovering Options for Exploration by Minimizing Cover Time. (arXiv:1903.00606v1 [cs.AI])

[ad_1] One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is...

Read more
Regret Minimisation in Multinomial Logit Bandits. (arXiv:1903.00543v1 [cs.AI])

[ad_1] We consider two regret minimisation problems over subsets of a finite ground set $[n]$, with subset-wise relative preference information feedback according to the Multinomial logit choice model. The first...

Read more
Aggregating explainability methods for neural networks stabilizes explanations. (arXiv:1903.00519v1 [cs.AI])

[ad_1] Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. In fact,...

Read more
Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group. (arXiv:1903.00206v1 [cs.AI])

[ad_1] Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action. In this paper, we define and quantify the intelligence level of heterogeneous agents group...

Read more
Should All Temporal Difference Learning Use Emphasis?. (arXiv:1903.00194v1 [cs.AI])

[ad_1] Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning...

Read more
To Monitor or to Trust: Observing Robot's Behavior based on a Game-Theoretic Model of Trust. (arXiv:1903.00111v1 [cs.AI])

[ad_1] In scenarios where a robot generates and executes a plan, there may be instances where this generated plan is less costly for the robot to execute but incomprehensible to...

Read more
Real-time tree search with pessimistic scenarios. (arXiv:1902.10870v1 [cs.AI])

[ad_1] Autonomous agents need to make decisions in a sequential manner, under partially observable environment, and in consideration of how other agents behave. In critical situations, such decisions need to...

Read more
Learning Task Knowledge and its Scope of Applicability in Experience-Based Planning Domains. (arXiv:1902.10770v1 [cs.AI])

[ad_1] Experience-based planning domains (EBPDs) have been recently proposed to improve problem solving by learning from experience. EBPDs provide important concepts for long-term learning and planning in robotics. They rely...

Read more
Unsupervised Grounding of Plannable First-Order Logic Representation from Images. (arXiv:1902.08093v1 [cs.AI])

[ad_1] Recently, there is an increasing interest in obtaining the relational structures of the environment in the Reinforcement Learning community. However, the resulting "relations" are not the discrete, logical predicates...

Read more
Probabilistic Relational Agent-based Models. (arXiv:1902.05677v1 [cs.AI])

[ad_1] PRAM puts agent-based models on a sound probabilistic footing as a basis for integrating agent-based and probabilistic models. It extends the themes of probabilistic relational models and lifted inference...

Read more
Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning. (arXiv:1902.05644v1 [cs.AI])

[ad_1] We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other...

Read more
Verifiably Safe Off-Model Reinforcement Learning. (arXiv:1902.05632v1 [cs.AI])

[ad_1] The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider...

Read more
State Duration and Interval Modeling in Hidden Semi-Markov Model for Sequential Data Analysis. (arXiv:1608.06954v2 [cs.AI] UPDATED)

[ad_1] Sequential data modeling and analysis have become indispensable tools for analyzing sequential data, such as time-series data, because larger amounts of sensed event data have become available. These methods...

Read more
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration. (arXiv:1902.05454v1 [cs.AI])

[ad_1] Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure ('Structured Procrastination') that provably...

Read more