arXiv research

Revel tackles safe exploration in RL with verified symbolic policies.

New method provides scalable safety guarantees for RL agents.

Safe RL with binary feedback using SABRE algorithm.

Safe exploration in RF-RL doesn't increase sample complexity.

Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.

New method tackles safe reinforcement learning from offline data.

The paper tackles safe exploration in RL by a conservative safety critic.

A new RL model ensures safe learning in uncertain environments.

The paper tackles safe reinforcement learning with convex regularization.

Safe reinforcement learning with logical constraints for optimal policy synthesis.

A novel approach for safe offline RL using latent safety constraints.

This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.

Safe offline RL for chemical reactors using input convex neural networks.

This paper proposes a method to safely adjust exploration in RL to satisfy constraints.

Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We describe and study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. First, we show how such a decomposition ar…

A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With the reward function, the RL agent learns to control vehicle speed in …

Hypotension in critical care settings is a life-threatening emergency that must be recognized and treated early. While fluid bolus therapy and vasopressors are common treatments, it is often unclear which interventions to give, in what amounts, and for how long. Observational data in the form of electronic health recor…

Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this…

ESRL uses uncertainty quantification to learn safe, optimal policies in offline RL.

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learnin…

Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converge…

Safe RL-based vibration control using LQR guidance.

Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box predictions. This results in poor explainability of the behaviour of these systems, raising concerns as to their use in safety-critical applica…

This paper considers Safe Policy Improvement (SPI) in Batch Reinforcement Learning (Batch RL): from a fixed dataset and without direct access to the true environment, train a policy that is guaranteed to perform at least as well as the baseline policy used to collect the data. Our approach, called SPI with Baseline Boo…

In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot…

Paper establishes lower bounds and optimal algorithms for deployment-efficient RL.

We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the $Q$-value from finite past experience data. Greedy policies or even …

New RL approach tackles constrained Markov decision processes.

Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.

Safe RL in linear systems achieves $\sqrt{T}$-regret.

Early detection of cyber-attacks is crucial for a safe and reliable operation of the smart grid. In the literature, outlier detection schemes making sample-by-sample decisions and online detection schemes requiring perfect attack models have been proposed. In this paper, we formulate the online attack/anomaly detection…

The operational space of an autonomous vehicle (AV) can be diverse and vary significantly. This may lead to a scenario that was not postulated in the design phase. Due to this, formulating a rule based decision maker for selecting maneuvers may not be ideal. Similarly, it may not be effective to design an a-priori cost…

CARL safely adapts RL agents for safety-critical tasks.

Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…

A new method improves actor-critic RL by integrating HMC, enhancing policy distribution and exploration.

CQL (ReDS) learns from varied driving behaviors, improving offline RL performance.

SECRM-2D improves RL-based autonomous driving with safety guarantees.

Survey of RL methods for control systems with time delays.

VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.

We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL in real-world problems. Despite its importance, existing general methods either h…

Improved RL policies from offline data with relaxed BC constraints.

The use of Reinforcement Learning (RL) is still restricted to simulation or to enhance human-operated systems through recommendations. Real-world environments (e.g. industrial robots or power grids) are generally designed with safety constraints in mind implemented in the shape of valid actions masks or contingency con…

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …

RRPI improves offline RL by optimizing policies against worst-case dynamics.

A new policy switching technique improves offline RL performance.

Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.

UVU simplifies value uncertainty quantification in RL.