Følg
Philip J. Ball
Philip J. Ball
Google DeepMind
Verifisert e-postadresse på google.com - Startside
Tittel
Sitert av
Sitert av
År
Active inference: demystified and compared
N Sajid, PJ Ball, T Parr, KJ Friston
Neural Computation 33 (3), 2021
1992021
Efficient Online Reinforcement Learning with Offline Data
PJ Ball*, L Smith*, I Kostrikov*, S Levine
ICML 2023, 2023
1652023
Revisiting Design Choices in Model-Based Offline Reinforcement Learning
C Lu*, PJ Ball*, J Parker-Holder, MA Osborne, SJ Roberts
ICLR 2022 (Spotlight), 2022
75*2022
Synthetic Experience Replay
C Lu*, PJ Ball*, J Parker-Holder
NeurIPS 2023, 2023
742023
The sensitivity of counterfactual fairness to unmeasured confounding
N Kilbertus, PJ Ball, MJ Kusner, A Weller, R Silva
UAI 2019, 2019
732019
Ready policy one: World building through active learning
P Ball*, J Parker-Holder*, A Pacchiano, K Choromanski, S Roberts
ICML 2020, 2020
572020
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
C Lu*, PJ Ball*, TGJ Rudner, J Parker-Holder, MA Osborne, YW Teh
TMLR, 2023
522023
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
PJ Ball*, C Lu*, J Parker-Holder, S Roberts
ICML 2021, 2021
482021
Same State, Different Task: Continual Reinforcement Learning without Interference
S Kessler, J Parker-Holder, P Ball, S Zohren, SJ Roberts
AAAI-22, 2022
472022
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
E Cetin*, PJ Ball*, S Roberts, O Celiktutan
ICML 2022, 2022
432022
Towards Tractable Optimism in Model-Based Reinforcement Learning
A Pacchiano*, P Ball*, J Parker-Holder*, K Choromanski, S Roberts
UAI 2021, 2021
41*2021
Bayesian Generational Population-Based Training
X Wan, C Lu, J Parker-Holder, PJ Ball, V Nguyen, B Ru, M Osborne
First Conference on Automated Machine Learning (Main Track), 2022
222022
Learning General World Models in a Handful of Reward-Free Deployments
Y Xu*, J Parker-Holder*, A Pacchiano*, PJ Ball*, O Rybkin, SJ Roberts, ...
NeurIPS 2022, 2022
112022
UNCLEAR: A Straightforward Method for Continual Reinforcement Learning
S Kessler, J Parker-Holder, P Ball, S Zohren, SJ Roberts
ICML 2020 Workshop on Continual Learning, 2020
82020
OffCon: What is state of the art anyway?
PJ Ball, SJ Roberts
arXiv preprint arXiv:2101.11331, 2021
62021
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
R Rafailov, K Hatch, A Singh, L Smith, A Kumar, I Kostrikov, ...
arXiv preprint arXiv:2408.08441, 2024
52024
A Study on Efficiency in Continual Learning Inspired by Human Learning
PJ Ball, Y Li, A Lamb, C Zhang
NeurIPS 2020 BabyMind Workshop, 2020
22020
Fairness in Machine Learning with Causal Reasoning
P Ball
MPhil Thesis, 2018
12018
Genie 2: A Large-Scale Foundation World Model
https://deepmind.google/discover/blog/genie-2-a-large-scale-foundation-world …, 2024
2024
Effective offline training and efficient online adaptation
P Ball
University of Oxford, 2023
2023
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20