arXiv research

SafePILCO is a Python tool for safe reinforcement learning.

Safe reinforcement learning framework using optimal transport for robustness.

CoCoRL learns safe constraints from demonstrations with unknown rewards.

Risk-averse model uncertainty framework for safe reinforcement learning.

SAMBA improves safe reinforcement learning with active exploration metrics.

Safe RL with binary feedback using SABRE algorithm.

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do …

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adve…

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.

Safe-M$^3$-UCRL learns safe policies for multi-agent systems with global constraints.

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

New method tackles safe reinforcement learning from offline data.

Revel tackles safe exploration in RL with verified symbolic policies.

New method provides scalable safety guarantees for RL agents.

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

Aims to create safe reinforcement learning policies by considering individual harm.

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…

Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.

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

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

This work establishes safe reinforcement learning for LQR with nonlinear baselines.

Machine learning can provide efficient solutions to the complex problems encountered in autonomous driving, but ensuring their safety remains a challenge. A number of authors have attempted to address this issue, but there are few publicly-available tools to adequately explore the trade-offs between functionality, scal…

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For such a problem, we construct a sequence of surrogate convex constrained optimiza…

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact the…

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

Safe-FinRL uses DRL for high-frequency stock trading, reducing bias and variance.

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 …

The paper tackles safe reinforcement learning with convex regularization.

Safe-EF improves federated learning for non-smooth, constrained optimization.

Tail-Safe hedging uses reinforcement learning with a safety layer to manage financial risks.

FISAR uses neural networks to optimize safe reinforcement learning with forward-invariant constraints.

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal, expressed as a temporal logic formula, with maximal probability. Enforcing the RL agen…

A new RL model ensures safe learning in uncertain environments.

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

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

Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…

Proposes Constrained Q-learning for reinforcement learning with constraints.

This paper addresses the question of how a previously available control policy $π_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $π_L$ for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the superv…

Paper proposes Vertex Networks for reinforcement learning of control systems with safety guarantees.

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

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consist…

Safe reinforcement learning tackles safety constraints with linear approximations.

Study improves self-driving safety in dynamic environments.

CRPO solves challenging SRL problems with convergence guarantee.

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…

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

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