CPSS projects cumulative safety constraints into time-varying per-state thresholds for online action shielding in nonstationary RL, providing per-state guarantees and cumulative bounds.
arXiv preprint arXiv:2402.02025 , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LILAC+ combines context-based, adaptation-speed, and budget-to-state safety constraints to reduce violations in continual RL under nonstationary conditions, demonstrated in simulated driving tasks.
Proposes a meta-RL framework combining latent context inference with distributional RL for safe, adaptive policy transfer across simulated and real CMDPs.
PRL-PUTS casts utility-weight tuning as a one-step value-based RL task and uses scalarization-parameter Pareto sweeping at inference time to generate and govern a family of policies, reporting +0.13% lift in successful sessions on Pinterest Homefeed.
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.
citing papers explorer
-
From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning
CPSS projects cumulative safety constraints into time-varying per-state thresholds for online action shielding in nonstationary RL, providing per-state guarantees and cumulative bounds.
-
Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
LILAC+ combines context-based, adaptation-speed, and budget-to-state safety constraints to reduce violations in continual RL under nonstationary conditions, demonstrated in simulated driving tasks.
-
Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment
Proposes a meta-RL framework combining latent context inference with distributional RL for safe, adaptive policy transfer across simulated and real CMDPs.
-
A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems
PRL-PUTS casts utility-weight tuning as a one-step value-based RL task and uses scalarization-parameter Pareto sweeping at inference time to generate and govern a family of policies, reporting +0.13% lift in successful sessions on Pinterest Homefeed.
-
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.