Imagen de Portada

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	K, Swaminathan S, Hazra, Aritra
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
por: Hazra, Somnath, et al.
Publicado: (2025)

DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning
por: Mani, Sabariswaran, et al.
Publicado: (2024)

SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL
por: Hu, Jiaheng, et al.
Publicado: (2025)

Sample-efficient and Scalable Exploration in Continuous-Time RL
por: Iten, Klemens, et al.
Publicado: (2025)

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

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
por: Park, Seohong, et al.
Publicado: (2023)

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
por: Yuan, Xiu, et al.
Publicado: (2024)

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
por: Kim, Changyeon, et al.
Publicado: (2025)

Safe Exploration via Policy Priors
por: Wendl, Manuel, et al.
Publicado: (2026)

CaRL: Learning Scalable Planning Policies with Simple Rewards
por: Jaeger, Bernhard, et al.
Publicado: (2025)

Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
por: Guo, Jian-Ting, et al.
Publicado: (2025)

Harnessing Bounded-Support Evolution Strategies for Policy Refinement
por: Hirschowitz, Ethan, et al.
Publicado: (2025)

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
por: Wagenmaker, Andrew, et al.
Publicado: (2025)

A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control
por: Choi, Wonhyeok, et al.
Publicado: (2026)

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
por: Xiao, Wei, et al.
Publicado: (2025)

First Order Model-Based RL through Decoupled Backpropagation
por: Amigo, Joseph, et al.
Publicado: (2025)

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration
por: Jin, Yang, et al.
Publicado: (2025)

Extremum-Seeking Action Selection for Accelerating Policy Optimization
por: Chang, Ya-Chien, et al.
Publicado: (2024)

Real-Time Execution of Action Chunking Flow Policies
por: Black, Kevin, et al.
Publicado: (2025)

Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
por: Kong, Lingxiao, et al.
Publicado: (2026)

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
por: Wu, Yilin, et al.
Publicado: (2025)

Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior
por: Cai, Shizhe, et al.
Publicado: (2025)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
por: Terence, Ng Wen Zheng, et al.
Publicado: (2024)

Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion
por: Chen, Kaiqi, et al.
Publicado: (2024)

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
por: Hong, Matthew M., et al.
Publicado: (2026)

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
por: Jin, Yang, et al.
Publicado: (2025)

Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
por: Patel, Bhrij, et al.
Publicado: (2023)

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization
por: Sukhija, Bhavya, et al.
Publicado: (2024)

GRAIL: Goal Recognition Alignment through Imitation Learning
por: Elhadad, Osher, et al.
Publicado: (2026)

AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement
por: Singh, Shivam, et al.
Publicado: (2025)

Align and Filter: Improving Performance in Asynchronous On-Policy RL
por: Honari, Homayoun, et al.
Publicado: (2026)

Grounding Video Models to Actions through Goal Conditioned Exploration
por: Luo, Yunhao, et al.
Publicado: (2024)

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
por: Pappalardo, Octavio
Publicado: (2026)

Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
por: Yokozawa, Riko, et al.
Publicado: (2025)

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

Stochastic Q-learning for Large Discrete Action Spaces
por: Fourati, Fares, et al.
Publicado: (2024)

Automatic Environment Shaping is the Next Frontier in RL
por: Park, Younghyo, et al.
Publicado: (2024)

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
por: Park, Seohong, et al.
Publicado: (2023)

Language-Conditioned Offline RL for Multi-Robot Navigation
por: Morad, Steven, et al.
Publicado: (2024)

Investigating Memory in Model-Free RL with POPGym Arcade
por: Wang, Zekang, et al.
Publicado: (2025)