Publications

	Synthetic Experience Replay Cong Lu*, Philip J. Ball*, Yee Whye Teh, Jack Parker-Holder NeurIPS 2023 Reincarnating Reinforcement Learning Workshop at ICLR 2023 (Spotlight), ICML 2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems [arXiv][Code]
	Efficient Online Reinforcement Learning with Offline Data Philip J. Ball*, Laura Smith*, Ilya Kostrikov*, Sergey Levine ICML 2023 [arXiv][Official][Code]
	Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations Cong Lu*, Philip J. Ball*, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh TMLR (2023) [arXiv][Official][Code]
	Learning General World Models in a Handful of Reward-Free Deployments Yingchen Xu*, Jack Parker-Holder*, Aldo Pacchiano*, Philip J. Ball*, Oleh Rybkin, Stephen J. Roberts, Tim Rocktäschel, Edward Grefenstette NeurIPS 2022 [arXiv][Official][Site]
	Stabilizing Off-Policy Deep Reinforcement Learning from Pixels Edoardo Cetin*, Philip J. Ball*, Stephen Roberts, Oya Celiktutan ICML 2022 [arXiv][Official]
	Revisiting Design Choices in Model-Based Offline Reinforcement Learning Cong Lu*, Philip J. Ball*, Jack Parker-Holder, Michael A. Osborne, Stephen Roberts ICLR 2022 (Spotlight, top 6.9% of all submissions) Spotlight at "RL4RealLife Workshop" @ ICML2021 [arXiv][Official]
	Same State, Different Task: Continual Reinforcement Learning without Interference Samuel Kessler, Jack Parker-Holder, Philip J. Ball, Stefan Zohren, Stephen Roberts AAAI 2022 [arXiv]
	Towards Tractable Optimism in Model-Based Reinforcement Learning Aldo Pacchiano*, Philip J. Ball*, Jack Parker-Holder*, Krzysztof Choromanski, Stephen Roberts UAI 2021 [arXiv][Official]
	Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment Philip J. Ball*, Cong Lu*, Jack Parker-Holder, Stephen Roberts ICML 2021 Spotlight at "Self-Supervision for Reinforcement Learning Workshop" @ ICLR 2021 [arXiv][Official][Website][Presentation]
	Active Inference: Demystified and Compared Noor Sajid*, Philip J. Ball*, Thomas Parr, Karl J. Friston Neural Computation (2021, Journal) [arXiv][Official][GitHub]
	Ready Policy One: World Building Through Active Learning Philip J. Ball*, Jack Parker-Holder*, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts ICML 2020 [arXiv][Official][GitHub][Media Coverage][Google Research Site]
	The Sensitivity of Counterfactual Fairness to Unmeasured Confounding Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva UAI 2019 [arXiv][Official][GitHub]

Workshop Papers

	A Study on Efficiency in Continual Learning Inspired by Human Learning Philip J. Ball, Yingzhen Li, Angus Lamb, Cheng Zhang BabyMind Workshop NeurIPS 2020 [arXiv]
	UNCLEAR: A Straightforward Method for Continual Reinforcement Learning Samuel Kessler, Jack Parker-Holder, Philip J. Ball, Stefan Zohren, Stephen J Roberts Workshop on Continual Learning ICML 2020 [Link][Official][Video]

Pre-Prints/Other

	OffCon3: What is state of the art anyway? Philip J. Ball, Stephen J. Roberts arXiv [arXiv][GitHub]
	Fairness in Machine Learning with Causal Reasoning Philip J. Ball, supervised by Dr. Adrian Weller MPhil Thesis [Thesis][Official]