3 citations · 3 across the 13 of their papers we have counts for
14 papers
Verifier-Guided Model Discovery for Physical Dynamical Systems with Pretrained Symbolic Transformers
Farbod Faraji, Francesco Belardinelli
Reliable forecasting of nonlinear physical systems underpins scientific discovery and engineering decision-making. Yet high-fidelity simulations are prohibitively costly, and machi…
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
Alexander W. Goodall, Francesco Belardinelli
Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we…
Synthesis of Safety Specifications for Probabilistic Systems
Gaspard Ohlmann, Edwin Hamel-De le Court, Francesco Belardinelli
Ensuring that agents satisfy safety specifications can be crucial in safety-critical environments. While methods exist for controller synthesis with safe temporal specifications, m…
Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
Alexander W. Goodall, Edwin Hamel-De le Court, Francesco Belardinelli
Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due…
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
Tiberiu-Andrei Georgescu, Alexander W. Goodall, Dalal Alrajeh +2
Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approac…
ProSh: Probabilistic Shielding for Model-free Reinforcement Learning
Edwin Hamel-De le Court, Gaspard Ohlmann, Francesco Belardinelli
Safety is a major concern in reinforcement learning (RL): we aim at developing RL systems that not only perform optimally, but are also safe to deploy by providing formal guarantee…
Probabilistic Shielding for Safe Reinforcement Learning
Edwin Hamel-De le Court, Francesco Belardinelli, Alexander W. Goodall
In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attenti…
Convergence and Connectivity: Dynamics of Multi-Agent Q-Learning in Random Networks
Dan Leonte, Aamal Hussain, Raphael Huser +2
Beyond specific settings, many multi-agent learning algorithms fail to converge to an equilibrium solution, instead displaying complex, non-stationary behaviours such as recurrent…
Measuring Goal-Directedness
Matt MacDermott, James Fox, Francesco Belardinelli +1
We define maximum entropy goal-directedness (MEG), a formal measure of goal-directedness in causal models and Markov decision processes, and give algorithms for computing it. Measu…
On the Stability of Learning in Network Games with Many Players
Aamal Hussain, Dan Leonte, Francesco Belardinelli +1
Multi-agent learning algorithms have been shown to display complex, unstable behaviours in a wide array of games. In fact, previous works indicate that convergent behaviours are le…
The Reasons that Agents Act: Intention and Instrumental Goals
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli +2
Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility,…
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
Alexander W. Goodall, Francesco Belardinelli
Shielding is a popular technique for achieving safe reinforcement learning (RL). However, classical shielding approaches come with quite restrictive assumptions making them difficu…
Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos
Aamal Hussain, Francesco Belardinelli
The behaviour of multi-agent learning in competitive network games is often studied within the context of zero-sum games, in which convergence guarantees may be obtained. However,…
Honesty Is the Best Policy: Defining and Mitigating AI Deception
Francis Rhys Ward, Francesco Belardinelli, Francesca Toni +1
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (…