TRAM is a test-time mixture method that scores and composes risk-neutral source policies using reward and occupancy-based risk to achieve new reward-risk tradeoffs without parameter updates.
Learning to be safe: Deep rl with a safety critic.arXiv preprint arXiv:2010.14603, 2020
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
UniIntervene uses future-conditioned action-value estimation and a temporal value-risk critic to trigger memory-based recovery interventions, reporting 8.6% higher success rates and 57% fewer human interventions than prior HiL-RL methods on real manipulation tasks.
Safe continual RL methods face a fundamental tension between enforcing safety constraints and preventing catastrophic forgetting in non-stationary environments, with regularization providing only partial mitigation.
SHAPO adds a sharpness-aware adjustment to policy optimization that reweights gradients to favor conservative behavior in uncertain areas, yielding better safety-performance tradeoffs on continuous control tasks.
Introduces the Adversarial Rate metric and associated tools to systematically evaluate and visualize the impact of adversarial inputs on DRL policies using formal verification.
citing papers explorer
-
TRAM: Test-Time Risk Adaptation with Mixture of Agents
TRAM is a test-time mixture method that scores and composes risk-neutral source policies using reward and occupancy-based risk to achieve new reward-risk tradeoffs without parameter updates.
-
UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
UniIntervene uses future-conditioned action-value estimation and a temporal value-risk critic to trigger memory-based recovery interventions, reporting 8.6% higher success rates and 57% fewer human interventions than prior HiL-RL methods on real manipulation tasks.
-
Safe Continual Reinforcement Learning in Non-stationary Environments
Safe continual RL methods face a fundamental tension between enforcing safety constraints and preventing catastrophic forgetting in non-stationary environments, with regularization providing only partial mitigation.
-
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
SHAPO adds a sharpness-aware adjustment to policy optimization that reweights gradients to favor conservative behavior in uncertain areas, yielding better safety-performance tradeoffs on continuous control tasks.
-
Analyzing Adversarial Inputs in Deep Reinforcement Learning
Introduces the Adversarial Rate metric and associated tools to systematically evaluate and visualize the impact of adversarial inputs on DRL policies using formal verification.