Philip Ball
6 papers · 2020–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge π Conference Polyglot (5)
π
Cross-Pollinator
(15)
π
Grand Slam
Conferences
NIPS (2)
AAAI (1)
ICLR (1)
ICML (1)
UAI (1)
Top co-authors
Keywords
reinforcement learning
(2)
continuous control
(2)
model-based reinforcement learning
(2)
sample efficiency
(2)
world model
(2)
active learning
(2)
value function estimation
(1)
multi-armed bandit
(1)
regret bound
(1)
diffusion model
(1)
synthetic datum
(1)
zero-shot generalization
(1)
reward-free exploration
(1)
experience replay
(1)
self-supervised exploration
(1)
hybrid objective
(1)
factorized policy
(1)
optimism in uncertainty
(1)
information theory
(1)
synthetic experience replay
(1)
Papers
Synthetic Experience Replay
NIPS 2023
Learning General World Models in a Handful of Reward-Free Deployments
NIPS 2022
Same State, Different Task: Continual Reinforcement Learning without Interference
AAAI 2022
Revisiting Design Choices in Offline Model Based Reinforcement Learning
ICLR 2022
Towards tractable optimism in model-based reinforcement learning
UAI 2021
Ready Policy One: World Building Through Active Learning
ICML 2020