Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schramm, Liam, Boularias, Abdeslam
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Bellman Diffusion Models
di: Schramm, Liam, et al.
Pubblicazione: (2024)

Autoregressive Action Sequence Learning for Robotic Manipulation
di: Zhang, Xinyu, et al.
Pubblicazione: (2024)

One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation
di: Zhang, Xinyu, et al.
Pubblicazione: (2024)

Bounding Distributional Shifts in World Modeling through Novelty Detection
di: Jing, Eric, et al.
Pubblicazione: (2025)

LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement
di: Chang, Haonan, et al.
Pubblicazione: (2023)

DAP: Diffusion-based Affordance Prediction for Multi-modality Storage
di: Chang, Haonan, et al.
Pubblicazione: (2024)

Learning Visual Feature-Based World Models via Residual Latent Action
di: Zhang, Xinyu, et al.
Pubblicazione: (2026)

KARL: Kalman-Filter Assisted Reinforcement Learner for Dynamic Object Tracking and Grasping
di: Boyalakuntla, Kowndinya, et al.
Pubblicazione: (2025)

Continuous Monte Carlo Graph Search
di: Kujanpää, Kalle, et al.
Pubblicazione: (2022)

Object-Centric World Models Meet Monte Carlo Tree Search
di: Vakhitov, Rodion, et al.
Pubblicazione: (2026)

Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks
di: Triantafyllidis, Eleftherios, et al.
Pubblicazione: (2023)

Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
di: Park, Byoungwoo, et al.
Pubblicazione: (2026)

Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
di: Kruse, Liam A., et al.
Pubblicazione: (2025)

Scaling Manipulation Learning with Visual Kinematic Chain Prediction
di: Zhang, Xinyu, et al.
Pubblicazione: (2024)

Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies
di: Liu, Yuhan, et al.
Pubblicazione: (2025)

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
di: Ishfaq, Haque, et al.
Pubblicazione: (2023)

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
di: Li, Yunfei, et al.
Pubblicazione: (2025)

Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction
di: Zhang, Xinyu, et al.
Pubblicazione: (2025)

Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
di: Li, Jinghan, et al.
Pubblicazione: (2024)

The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrations
di: von Hartz, Jan Ole, et al.
Pubblicazione: (2024)

Single-Shot Learning of Stable Dynamical Systems for Long-Horizon Manipulation Tasks
di: St-Aubin, Alexandre, et al.
Pubblicazione: (2024)

Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
di: Kee, Hogun, et al.
Pubblicazione: (2025)

RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
di: Hu, Zheyuan, et al.
Pubblicazione: (2025)

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics
di: Yang, Heng
Pubblicazione: (2026)

Observation-Augmented Contextual Multi-Armed Bandits for Robotic Search and Exploration
di: Wakayama, Shohei, et al.
Pubblicazione: (2023)

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
di: Zhang, Zhilong, et al.
Pubblicazione: (2026)

Refining Compositional Diffusion for Reliable Long-Horizon Planning
di: Lee, Kyowoon, et al.
Pubblicazione: (2026)

Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO Optimization
di: Salloum, Hadi, et al.
Pubblicazione: (2026)

First-order Sobolev Reinforcement Learning
di: Schramm, Fabian, et al.
Pubblicazione: (2025)

Monte Carlo Tree Search with Boltzmann Exploration
di: Painter, Michael, et al.
Pubblicazione: (2024)

Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion
di: Geiß, Henri-Jacques, et al.
Pubblicazione: (2024)

TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments
di: Hossain, Jumman, et al.
Pubblicazione: (2024)

ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
di: Du, Yurui, et al.
Pubblicazione: (2026)

Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines
di: Lin, Yu-An, et al.
Pubblicazione: (2023)

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
di: Venugopal, Aravind, et al.
Pubblicazione: (2026)

Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
di: Pan, Yiyuan, et al.
Pubblicazione: (2025)

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems
di: Cherepanov, Egor, et al.
Pubblicazione: (2025)

Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning
di: Shen, Chengyandan, et al.
Pubblicazione: (2025)

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves
di: Xu, Pei, et al.
Pubblicazione: (2025)

λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics
di: Jaafar, Ahmed, et al.
Pubblicazione: (2024)