Article

PokerOWL: A Multi-Agent Poker Environment for Implementing and Evaluating Open-World Learning

2024-07-26

Abstract excerpt

<title>Abstract</title> <p>In complex task environments in both nature and human society, structural violations of expectation (VoE) occur with non-trivialfrequency. Agents that are designed to operate in such environments must be capable of open-world learning (OWL), definedas the ability to detect and accommodate out-of-distribution inputs, as well as more complex structural VoEs, without requiringextensive and...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4d9c114d-421d-5a00-b6ee-4fe21c5d5a8b
DOI: 10.21203/rs.3.rs-4677706/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

PokerOWL: A Multi-Agent Poker Environment for Implementing and Evaluating Open-World LearningDOI 10.21203/rs.3.rs-4677706/v1Read

Learning Safe Behaviour via Justified Human Preferences and Hypothetical QueriesSemantic proximity Read

A Policy-Graph Approach to Explain Reinforcement Learning Agents: A Novel Policy-Graph Approach with Natural Language and Counterfactual Abstractions for Explaining Reinforcement Learning AgentsSemantic proximity Read

Multi-Agent based Dynamic Anchors for Interpretation of Deep Learning ClassifiersSemantic proximity Read

Learning Safe Behaviour via Justified Human Preferences and Hypothetical QueriesSemantic proximity Read

Preserving and combining knowledge in robotic lifelong reinforcement learningSemantic proximity Read

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

Road to AGI: The Importance of Clear Objectives and Reward FunctionsSemantic proximity Read

Advances in deep reinforcement learning enable better predictions of human behavior in time-continuous tasksSemantic proximity Read

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science PerformanceSemantic proximity Read

From Pre-Trained Language Models to Agentic AI: Evolution and Architectures for Autonomous IntelligenceSemantic proximity Read

The World Is a Hypothesis: Epistemic Control for Executable World-Model Agents in Novel Interactive EnvironmentsSemantic proximity Read

Reinforcement learning under uncertainty: expected versus unexpected uncertainty and state versus reward uncertaintySemantic proximity Read