6 papers
Ground-Truth-First Benchmarking of Reinforcement Learning via Converse Optimality: From Smooth, Fully Observed Systems to Non-Smooth or Partially Observed Tasks
Grégoire Ouerdane, Sinan Ibrahim, Stefan Streif +1
Benchmarking in reinforcement learning is usually relative: algorithms are ranked by returns on environments with unknown optima. Distance to optimality remains unobservable, while…
An Agency-Transferring Model-Free Policy Enhancement Technique
Anton Bolychev, Georgiy Malaniya, Sinan Ibrahim +1
Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation. Yet many con…
Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies
Sinan Ibrahim, Grégoire Ouerdane, Hadi Salloum +3
The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sen…
Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets
Hadi Salloum, Maximilian Mifsud Bonici, Sinan Ibrahim +2
Physics-Informed Neural Networks (PINNs) enforce governing equations by penalizing PDE residuals at interior collocation points, but standard collocation strategies - uniform sampl…
Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent
Pavel Osinenko, Grigory Yaremenko, Roman Zashchitin +3
This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words,…
Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications
Sinan Ibrahim, Mostafa Mostafa, Ali Jnadi +2
The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and e…