Get started
Author

Alexander W. Goodall

Observed names: Alex W. Goodall, Goodall, Alex, Goodall, Alexander W.
Observed institution: Imperial College London
ORCID: 0000-0003-4659-5241
Observed ORCID: 0000-0003-4659-5241
OpenAlex ID: A5035327010
Probabilistic Shielding for Safe Reinforcement Learning
2025 · Edwin Hamel-De le Court, Francesco Belardinelli, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 10
PDF
Approximate Model-Based Shielding for Safe Reinforcement Learning
2023 · Alexander W. Goodall, Francesco Belardinelli · Frontiers in artificial intelligence and applications · 7
PDF
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
2024 · Alexander W. Goodall, Francesco Belardinelli · Adaptive Agents and Multi-Agents Systems · 4
PDF
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
2026 · Goodall, Alexander W., Belardinelli, Francesco · arXiv (Cornell University) · 2
PDF
Approximate Shielding of Atari Agents for Safe Exploration
2023 · Goodall, Alexander W., Belardinelli, Francesco · arXiv (Cornell University) · 2
PDF
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
2026 · Alexander W. Goodall, Francesco Belardinelli · Adaptive Agents and Multi-Agents Systems · 1
Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
2026 · Alex W. Goodall, Edwin Hamel-De Le Court, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
2025 · Goodall, Alexander W., Court, Edwin Hamel-De le, et al. · arXiv (Cornell University) · 1
PDF
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
2025 · Georgescu, Tiberiu-Andrei, Goodall, Alexander W., et al. · arXiv (Cornell University) · 1
PDF
RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
2026 · Goodall, Alexander W., Belardinelli, Francesco · arXiv (Cornell University)
PDF
1286 - Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-policy Reinforcement Learning
2026 · Association for Artificial Intelligence 2026, Belardinelli, Francesco, et al. · Underline Science Inc.
Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
2026 · Association for Artificial Intelligence 2026, Belardinelli, Francesco, et al. · Underline Science Inc.
Works count: 13
Citation count: 30
H-index: 3
I10-index: 1
Year
Topic
Type