Safe exploration framework for IML algorithms.
problem Safe decision-making in IML without unsafe outcomes.
method Exploits Gaussian process prior to efficiently learn safe decisions.
result Outperforms other algorithms empirically.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “unsafe exploration”
Safe actions learned in finite trials, without infinite exploration.
problem Learning safe actions in unknown environments efficiently.
method Defining a handicap metric and using sequential probability ratio test for discarding unsafe actions.
result Achieves constant handicap, discarding unsafe machines with probability one in finite rounds.
Parenting algorithm improves AI safety by learning from human input.
problem Safety concerns in reinforcement learning, especially reward hacking and unsafe exploration.
method Inspired by parenting, a precise framework for learning from human input.
result Parenting algorithm solves safety problems in AI Safety gridworlds.
We develop a method to estimate the time to unsafe responses in LLMs.
problem Estimating the time to unsafe responses in large language models is challenging due to the rarity of unsafe outputs.
method We frame the problem as survival analysis and propose a calibration technique for constructing a lower predictive bound (LPB).
result Our method provides rigorous coverage guarantees and improves sample efficiency.
AST provides a method to validate safe autonomy without unsafe simplifications.
problem Validation of safe autonomy in complex systems.
method Adaptive Stress Testing (AST) approach.
result AST can find failures without unsafe simplifications.
In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…
Enhances reinforcement learning safety through risk-averse exploration.
problem Safety concerns in reinforcement learning due to sub-optimal actions.
method Distributionally robust policy iteration scheme with lower bound guarantees.
result Efficient algorithm that prevents poor decisions and converges to optimal policy.
The paper tackles safe exploration in RL by a conservative safety critic.
problem Safe exploration in reinforcement learning (RL) when partially trained policies are deployed.
method Learning a conservative safety estimate through a critic, provably bounding catastrophic failures.
result The approach provably converges to competitive task performance with significantly lower catastrophic failure rates.
Simple online monitor detects unsafe LLM outputs.
problem LLMs generate unsafe outputs despite training.
method Thresholding external verifier signal to decide alarms.
result Simple design competitive with advanced methods.
Safe RL with binary feedback using SABRE algorithm.
problem Safe reinforcement learning with binary safety feedback.
method SABRE algorithm, combining active learning and reinforcement learning.
result Provable safe policy with high probability, no unsafe actions during training.
COCA refactors training data to identify and erase unsafe concepts in LLMs.
problem Identifying and erasing unsafe concepts in Large Language Models (LLMs) for safety alignment.
method Concept Concentration (COCA) refactors training data with an explicit reasoning process to identify and erase unsafe concepts.
result COCA significantly reduces both in-distribution and out-of-distribution jailbreak success rates while maintaining strong performance on regular tasks.
New algorithm learns safe policies in unknown environments.
problem Learning safe policies in unknown, potentially unsafe environments.
method C-UCRL: Upper Confidence Reinforcement Learning for constrained MDPs.
result Achieves sub-linear regret while satisfying constraints.
Algorithm learns user's reward function from hypothetical behaviors.
problem Aligning agent behavior with unknown user objectives.
method Synthesizes hypothetical behaviors, asks user for rewards, trains neural network.
result Significantly outperforms prior methods in learning reward models.
A new method improves actor-critic RL by integrating HMC, enhancing policy distribution and exploration.
problem Actor-critic RL yields suboptimal policies due to amortization gap and insufficient exploration.
method Integrating Hamiltonian Monte Carlo (HMC) into the actor-critic RL framework.
result Improves policy distribution and exploration, leading to better policy estimates and higher returns.
New framework for efficient query-based imitation learning.
problem Aligning agent policy with human expert behavior without prior knowledge.
method Adversarial reward query with successor representation.
result Significantly outperforms uncertainty-based methods in query efficiency.
Safe reinforcement learning tackles safety constraints with linear approximations.
problem Ensuring safety in reinforcement learning without violating constraints.
method Modeling safety as a linear cost function, developing SLUCB-QVI and RSLUCB-QVI algorithms for MDPs with linear function approximation.
result Achieved a nearly optimal regret bound for safe reinforcement learning, matching state-of-the-art unsafe algorithms.
Neural network predicts nonlinear safety behavior based on personality traits.
problem Predicting construction workers' unsafe behaviors based on personality traits.
method Developed a forecasting model using neural network algorithms.
result Nonlinear relationship exists between personality traits and safety behavior.
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectoriescs.LG
OSIL learns safe policies from unsafe demonstrations.
problem Offline safe imitation learning with implicit safety.
method Formulates CMDP, infers safety from non-preferred trajectories, learns cost model.
result OSIL learns safer policies without degrading reward performance.
Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.
problem Maximizing reward while avoiding unsafe arms under safety risk constraints.
method Doubly optimistic strategies with pseudo-regret formulation.
result Logarithmic regret bounds for safe multi-armed bandits.
Theoretical analysis confirms non-conservative algorithms can converge to optimal policies.
problem Theoretical guarantees for non-conservative reinforcement learning algorithms.
method Theoretical analysis of Peng's Q() algorithm.
result Peng's Q() converges to an optimal policy under certain conditions.
Proposes an RL algorithm for handling convex constraints.
problem Handling constraints in reinforcement learning.
method Algorithm for convex constraints in RL.
result Algorithm can enforce new properties like diversity.
Study optimality in safety-constrained Markov decision processes using asynchronous value iteration and modified Q-learning.
problem Optimality in safety-constrained Markov decision processes with multichain structure.
method Formulated as a zero-sum game, constructed asynchronous value iteration scheme and modified Q-learning algorithm.
result Resolved Bellman's principle of optimality for multichain Markov decision processes and provided learning algorithms.
H-ReIL learns to drive safely in near-accident scenarios.
problem Driving safely in high-risk near-accident situations.
method Hierarchical RL and IL approach.
result High-level policy switches between low-level policies for safe driving.
New bounds on trajectory safety in training models with Langevin Dynamics.
problem Bounding the probability of a model's trajectory staying away from a designated failure region.
method Analyzes Langevin dynamics on smooth, strongly convex loss landscapes, introducing shape-free and local relaxation bounds.
result The in-set probability relaxes to the static value after a burn-in time of order d, using only the global spectral gap of the loss.
DRSSS method reduces model training costs by eliminating unsafe samples.
problem Reducing storage and training costs for customized models across different environments.
method Combines DR optimization and SSS for covariate shift.
result Models trained on reduced dataset perform similarly to those on full dataset.
Framework trains safe agents avoiding deceptive behavior.
problem Training safe agents from unsafe incentives.
method Formal settings, causal influence analysis, maximizing non-mediated effects.
result Agents avoid manipulating delicate state for rewards.
A new algorithm trains experts to safely guide agents in partially observed environments.
problem Existing imitation learning methods for POMDPs can lead to sub-optimal or unsafe policies.
method Derive an objective to encourage the expert to maximize the agent's reward, then use it to train both expert and agent.
result The algorithm produces an expert policy that the agent can safely imitate, outperforming fixed expert policies.
HardVis helps visually manage imbalanced data by sampling hard instances.
problem Managing unsafe or noisy instances in imbalanced classification.
method Visual analytics system using undersampling and oversampling techniques.
result Boosts predictive power of ML models by balancing data sets.
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and act safely around them. We argue that most current approaches that learn from hu…
Investigates safe decision-making in interactive environments.
problem Learning the best safe decision in real-time systems.
method Reduces to a constrained linear bandits problem, proposes adaptive experimental design-based algorithm.
result First results on best-arm identification in linear bandits with safety constraints.
Meta-reinforcement learning improves fault-adaptive control efficiency.
problem Adaptive control under abrupt system faults with strict time constraints.
method Model-agnostic meta learning (MAML) with a fault library of prior policies.
result Improved sample efficiency and quick adaptation to new faults.
Neural Lyapunov Redesigneess.SY
Combines Lyapunov functions with controller synthesis for safe control policies.
problem Ensuring safety in controller design for nonlinear systems.
method Iterative algorithm combining Lyapunov function estimation and controller synthesis.
result Effective control policies with large safe regions are derived.
CoCoRL learns safe constraints from demonstrations with unknown rewards.
problem Learning safe constraints from demonstrations with different unknown rewards.
method Convex Constraint Learning for Reinforcement Learning (CoCoRL) constructs a convex safe set based on demonstrations.
result CoCoRL learns constraints that lead to safe driving behavior and can safely transfer to different tasks and environments.
FOCOPS optimizes agent's behavior while adhering to constraints.
problem Optimizing agent's behavior while respecting safety constraints.
method FOCOPS solves a constrained optimization problem in policy space, then projects the solution back into the parametric space.
result FOCOPS achieves better performance on constrained robotics tasks.
New method learns policies from offline data using operator models.
problem Limited understanding of approximation errors in offline reinforcement learning.
method Linking reinforcement learning to Hamilton-Jacobi-Bellman equation, proposing operator-theoretic algorithm.
result Global convergence of the value function and finite-sample guarantees derived.
New algorithm achieves sublinear regret in CMDPs without error cancellations.
problem Safety constraints in reinforcement learning with error cancellations.
method Model-based primal-dual algorithm for CMDPs with multiple constraints.
result Achieves sublinear regret without error cancellations.
Advanced driver assistance systems (ADAS) can be significantly improved with effective driver action prediction (DAP). Predicting driver actions early and accurately can help mitigate the effects of potentially unsafe driving behaviors and avoid possible accidents. In this paper, we formulate driver action prediction a…
Meta-KeL learns kernels from offline data to improve sequential decision-making.
problem Adaptive confidence sets for prediction functions in sequential decision-making tasks.
method Meta-KeL: meta-learning a kernel from offline data; structured sparsity estimator for unknown kernel combinations.
result Valid confidence sets that become as tight as those given the true unknown kernel with increasing offline data.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
New framework uses conformal predictions for robust, scalable machine learning classification.
problem Developing robust and reliable machine learning models for classification.
method Introducing scalable classifiers linked to statistical order theory and probabilistic learning theory, defining a score function and conformal safety set.
result Demonstrated practical implications in cybersecurity for identifying DNS tunneling attacks.
Why Stake When You Can Borrow?q-fin.GN
New model assesses risks of staking and borrowing in smart contracts.
problem Security and efficiency of staking in smart contract platforms.
method Combines birth-death Pólya processes and credit derivatives models.
result Derivatives can reduce wealth concentration in staking networks.
SAFER improves personalized treatment recommendations for dynamic clinical contexts.
problem Personalized treatment optimization in evolving clinical contexts with safety concerns.
method Integrates structured EHR and clinical notes, uses conformal prediction for safe recommendations.
result SAFER outperforms state-of-the-art baselines in recommendation metrics and mortality rates.
Study analyzes sensitivity of RL algorithm for ICU hemodynamic management.
problem Evaluating safety and reliability of RL in clinical settings.
method Sensitivity analysis of Duel-DDQN on ICU sepsis patients.
result RL policies are sensitive to various implementation factors.
Develops a theory to make learning solutions fair and safe.
problem Ensuring learning solutions are unbiased and safe in critical applications.
method Generates a generalization theory based on PAC learning framework, introduces constrained learning algorithm.
result Proves that constrained learning is as learnable as unconstrained learning, provides practical algorithm.
New analysis shows rational actors will deploy AGI despite negative social value due to catastrophic risk.
problem Rational actors will deploy AGI despite negative social value due to shared catastrophic risk.
method Continuous-time preemption game with shared catastrophic externalities, showing suicide region and welfare distortion.
result The suicide region widens as catastrophic risk grows, and two mechanisms can close it.
C3T-Budget optimizes drug efficacy in dose-finding trials with budget and safety constraints.
problem Heterogeneous patient populations and budget constraints make dose-finding clinical trials challenging.
method Contextual constrained clinical trial algorithm that maximizes drug efficacy while learning subgroup responses.
result Demonstrates efficient budget usage and balanced learning-treatment trade-off in simulated trials.
Interventional domain adaptation improves feature transferability by removing spurious correlations.
problem Improper feature transferability due to spurious correlations in domain adaptation.
method Intervention strategy using unlabeled target data to generate counterfactual features and train discriminability invariance.
result Consistent performance improvements over state-of-the-art approaches in various domain adaptation tasks.
Paper tackles constrained learning with non-convex losses, overcoming challenges with new approach.
problem Challenges in learning with non-convex losses and statistical constraints.
method Learning in the empirical dual domain, bounding empirical duality gap.
result Established a constrained counterpart to classical learning theory.