Copertina

Learning Abstract World Model for Value-preserving Planning with Options

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rodriguez-Sanchez, Rafael, Konidaris, George
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning
di: Rodriguez-Sanchez, Rafael, et al.
Pubblicazione: (2025)

Joint Learning of Hierarchical Neural Options and Abstract World Model
di: Piriyakulkij, Wasu Top, et al.
Pubblicazione: (2026)

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
di: Ahn, Hongjoon, et al.
Pubblicazione: (2025)

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
di: Tiwari, Saket, et al.
Pubblicazione: (2022)

Model-based Reinforcement Learning for Parameterized Action Spaces
di: Zhang, Renhao, et al.
Pubblicazione: (2024)

Knowledge Retention for Continual Model-Based Reinforcement Learning
di: Sun, Yixiang, et al.
Pubblicazione: (2025)

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
di: Tiwari, Saket, et al.
Pubblicazione: (2025)

OptionZero: Planning with Learned Options
di: Huang, Po-Wei, et al.
Pubblicazione: (2025)

Learning Markov State Abstractions for Deep Reinforcement Learning
di: Allen, Cameron, et al.
Pubblicazione: (2021)

Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains
di: Tao, Ruo Yu, et al.
Pubblicazione: (2025)

Latent-Predictive Empowerment: Measuring Empowerment without a Simulator
di: Levy, Andrew, et al.
Pubblicazione: (2024)

Exploiting Contextual Structure to Generate Useful Auxiliary Tasks
di: Quartey, Benedict, et al.
Pubblicazione: (2023)

Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network
di: Hsiao, Vincent, et al.
Pubblicazione: (2025)

Learning Parameterized Skills from Demonstrations
di: Gupta, Vedant, et al.
Pubblicazione: (2025)

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
di: Liang, Yichao, et al.
Pubblicazione: (2025)

Accelerating Residual Reinforcement Learning with Uncertainty Estimation
di: Dodeja, Lakshita, et al.
Pubblicazione: (2025)

Continual Reinforcement Learning by Planning with Online World Models
di: Liu, Zichen, et al.
Pubblicazione: (2025)

VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
di: Liang, Yichao, et al.
Pubblicazione: (2024)

From Abstract to Actionable: Pairwise Shapley Values for Explainable AI
di: Xu, Jiaxin, et al.
Pubblicazione: (2025)

From Noise to Control: Parameterized Diffusion Policies
di: Zhang, Renhao, et al.
Pubblicazione: (2026)

Compositional Planning with Jumpy World Models
di: Farebrother, Jesse, et al.
Pubblicazione: (2026)

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
di: Bredis, George, et al.
Pubblicazione: (2025)

Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
di: Orozco, Sergio, et al.
Pubblicazione: (2026)

CausalARC: Abstract Reasoning with Causal World Models
di: Maasch, Jacqueline, et al.
Pubblicazione: (2025)

Scalable Option Learning in High-Throughput Environments
di: Henaff, Mikael, et al.
Pubblicazione: (2025)

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
di: Wu, Hao, et al.
Pubblicazione: (2025)

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
di: Aminmansour, Farzane, et al.
Pubblicazione: (2020)

Language-guided Skill Learning with Temporal Variational Inference
di: Fu, Haotian, et al.
Pubblicazione: (2024)

Retrosynthetic Planning with Dual Value Networks
di: Liu, Guoqing, et al.
Pubblicazione: (2023)

Boosting deep Reinforcement Learning using pretraining with Logical Options
di: Ye, Zihan, et al.
Pubblicazione: (2026)

TRAP: Tail-aware Ranking Attack for World-Model Planning
di: Duan, Siyuan, et al.
Pubblicazione: (2026)

Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning
di: Shek, Chak Lam, et al.
Pubblicazione: (2025)

Unveiling Options with Neural Decomposition
di: Alikhasi, Mahdi, et al.
Pubblicazione: (2024)

Diversity-Enriched Option-Critic
di: Kamat, Anand, et al.
Pubblicazione: (2020)

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
di: Pandaram, Muthukumar, et al.
Pubblicazione: (2025)

Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning
di: Fan, Shanwei, et al.
Pubblicazione: (2025)

Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
di: Liu, Youwei, et al.
Pubblicazione: (2026)

Learning to Drive Safely with Hybrid Options
di: De Cooman, Bram, et al.
Pubblicazione: (2025)

Next Embedding Prediction Makes World Models Stronger
di: Bredis, George, et al.
Pubblicazione: (2026)

RLVR-World: Training World Models with Reinforcement Learning
di: Wu, Jialong, et al.
Pubblicazione: (2025)