Image de couverture de livre

Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jucys, Karolis, Adamopoulos, George, Hamidi, Mehrab, Milani, Stephanie, Samsami, Mohammad Reza, Zholus, Artem, Joseph, Sonia, Richards, Blake, Rish, Irina, Şimşek, Özgür
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mastering Memory Tasks with World Models
par: Samsami, Mohammad Reza, et autres
Publié: (2024)

Continuous Histogram Loss: Beyond Neural Similarity
par: Zholus, Artem, et autres
Publié: (2020)

Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions
par: Panayiotou, Panayiotis, et autres
Publié: (2026)

Shahname Firdausi and Transformational Management with Attitude Comparison Ulrich Transformation Pattern
par: Shirin Samsami
Publié: (2015)

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
par: Nilaksh, et autres
Publié: (2026)

Learning The Minimum Action Distance
par: Steccanella, Lorenzo, et autres
Publié: (2025)

Curricula for Learning Robust Policies with Factored State Representations in Changing Environments
par: Panayiotou, Panayiotis, et autres
Publié: (2024)

Approximating Shapley Explanations in Reinforcement Learning
par: Beechey, Daniel, et autres
Publié: (2025)

A Modular Measurement Integrity Verification for Transformer Currents with Applications in Hardware in-the-Loop Digital Twin
par: Hamidi, Reza Jalilzadeh
Publié: (2024)

CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models
par: Roger, Alexis, et autres
Publié: (2025)

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
par: Legate, Gwen, et autres
Publié: (2025)

Towards ethical multimodal systems
par: Roger, Alexis, et autres
Publié: (2023)

Accelerating Task Generalisation with Multi-Level Skill Hierarchies
par: Cannon, Thomas P, et autres
Publié: (2024)

Hierarchical Orchestra of Policies
par: Cannon, Thomas P, et autres
Publié: (2024)

Creating Multi-Level Skill Hierarchies in Reinforcement Learning
par: Evans, Joshua B., et autres
Publié: (2023)

Computational Framework for White Hole Detection in Gravitational Waves and CMB Data
par: Valamontes, Antonios, et autres
Publié: (2025)

Symposium on Misallocation and Structural Transformation: Introduction
par: Tasso Adamopoulos, et autres
Publié: (2024)

DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
par: Ren, Li, et autres
Publié: (2025)

THE RELATIONSHIP BETWEEN PRIVATE EQUITY AND ECONOMIC GROWTH
par: Karolis Gudiškis
Publié: (2015)

Reducing prejudice through biased group contact?
par: Karolis Dambrauskas
Publié: (2019)

EVALUATION OF FINANCIAL EFFECTS OF PUBLIC PROCUREMENT CENTRALISATION
par: Karolis Šerpytis
Publié: (2011)

Safe Liposuction: Case Report and Review of the Literature
par: Karolis Černauskis
Publié: (2020)

Novel human genome variants associated with alcohol use disorders identified in a Lithuanian cohort
par: Karolis Baronas
Publié: (2018)

PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation
par: Shang, Chikai, et autres
Publié: (2025)

Too Big to Fool: Resisting Deception in Language Models
par: Samsami, Mohammad Reza, et autres
Publié: (2024)

T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
par: Dizaji, Alireza, et autres
Publié: (2025)

VFA: Vision Frequency Analysis of Foundation Models and Human
par: Darvishi-Bayazi, Mohammad-Javad, et autres
Publié: (2024)

Interpreting Physics in Video World Models
par: Joseph, Sonia, et autres
Publié: (2026)

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
par: Cherepanov, Egor, et autres
Publié: (2024)

A Source-Independent Fault Detection Method for Transmission Lines
par: Hamidi, Reza Jalilzadeh, et autres
Publié: (2024)

Blockchain for Network Security_ Applications in Decentralized Security Protocolswe
par: Mehrab, Abu Imam Mehrab
Publié: (2025)

LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning
par: Ye, Zhuorui, et autres
Publié: (2024)

Knowledge Distillation for Federated Learning: a Practical Guide
par: Mora, Alessio, et autres
Publié: (2022)

Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context
par: de Margerie, Anatole Jacquin, et autres
Publié: (2025)

On the Adversarial Robustness of Discrete Image Tokenizers
par: Bhagwatkar, Rishika, et autres
Publié: (2026)

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
par: Riemer, Matthew, et autres
Publié: (2024)

Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
par: Li, Zaijing, et autres
Publié: (2025)

A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values
par: Beechey, Daniel, et autres
Publié: (2025)

Superluminal Dark Photons as a Solution to the GRB 221009A Anomaly
par: Valamontes, Antonios, et autres
Publié: (2025)

Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft
par: Kranti, Chalamalasetti, et autres
Publié: (2024)