144 citations · 233 across the 16 of their papers we have counts for
16 papers
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
Rafael Rafailov, Kyle Hatch, Anikait Singh +9
Offline reinforcement learning algorithms hold the promise of enabling data-driven RL methods that do not require costly or dangerous real-world exploration and benefit from large…
Synthetic Experience Replay
Cong Lu, Philip J. Ball, Yee Whye Teh +1
A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this pa…
Efficient Online Reinforcement Learning with Offline Data
Philip J. Ball, Laura Smith, Ilya Kostrikov +1
Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of…
Learning General World Models in a Handful of Reward-Free Deployments
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano +5
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate…
Bayesian Generational Population-Based Training
Xingchen Wan, Cong Lu, Jack Parker-Holder +4
Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittlen…
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Edoardo Cetin, Philip J. Ball, Steve Roberts +1
Off-policy reinforcement learning (RL) from pixel observations is notoriously unstable. As a result, many successful algorithms must combine different domain-specific practices and…
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Cong Lu, Philip J. Ball, Tim G. J. Rudner +3
Offline reinforcement learning has shown great promise in leveraging large pre-collected datasets for policy learning, allowing agents to forgo often-expensive online data collecti…
Revisiting Design Choices in Offline Model-Based Reinforcement Learning
Cong Lu, Philip J. Ball, Jack Parker-Holder +2
Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially…
Same State, Different Task: Continual Reinforcement Learning without Interference
Samuel Kessler, Jack Parker-Holder, Philip Ball +2
Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL i…
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Philip J. Ball, Cong Lu, Jack Parker-Holder +1
Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration. Significant progress…
OffCon: What is state of the art anyway?
Philip J. Ball, Stephen J. Roberts
Two popular approaches to model-free continuous control tasks are SAC and TD3. At first glance these approaches seem rather different; SAC aims to solve the entropy-augmented MDP b…
A Study on Efficiency in Continual Learning Inspired by Human Learning
Philip J. Ball, Yingzhen Li, Angus Lamb +1
Humans are efficient continual learning systems; we continually learn new skills from birth with finite cells and resources. Our learning is highly optimized both in terms of capac…
Towards Tractable Optimism in Model-Based Reinforcement Learning
Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder +2
The principle of optimism in the face of uncertainty is prevalent throughout sequential decision making problems such as multi-armed bandits and reinforcement learning (RL). To be…
Ready Policy One: World Building Through Active Learning
Philip Ball, Jack Parker-Holder, Aldo Pacchiano +2
Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However…
Active inference: demystified and compared
Noor Sajid, Philip J. Ball, Thomas Parr +1
Active inference is a first principle account of how autonomous agents operate in dynamic, non-stationary environments. This problem is also considered in reinforcement learning (R…
The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
Niki Kilbertus, Philip J. Ball, Matt J. Kusner +2
Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In…