Search Results for author: Philip J. Ball

Found 13 papers, 8 papers with code

Synthetic Experience Replay

1 code implementation NeurIPS 2023 Cong Lu, Philip J. Ball, Yee Whye Teh, Jack Parker-Holder

We believe that synthetic training data could open the door to realizing the full potential of deep learning for replay-based RL algorithms from limited data.

Reinforcement Learning (RL) Self-Supervised Learning

Bayesian Generational Population-Based Training

2 code implementations19 Jul 2022 Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael A. Osborne

Leveraging the new highly parallelizable Brax physics engine, we show that these innovations lead to large performance gains, significantly outperforming the tuned baseline while learning entire configurations on the fly.

Bayesian Optimization Reinforcement Learning (RL)

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

2 code implementations9 Jun 2022 Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh

Using this suite of benchmarking tasks, we show that simple modifications to two popular vision-based online reinforcement learning algorithms, DreamerV2 and DrQ-v2, suffice to outperform existing offline RL methods and establish competitive baselines for continuous control in the visual domain.

Benchmarking Continuous Control +3

Revisiting Design Choices in Offline Model-Based Reinforcement Learning

no code implementations8 Oct 2021 Cong Lu, Philip J. Ball, Jack Parker-Holder, Michael A. Osborne, Stephen J. Roberts

Significant progress has been made recently in offline model-based reinforcement learning, approaches which leverage a learned dynamics model.

Bayesian Optimization Model-based Reinforcement Learning +2

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

no code implementations ICLR Workshop SSL-RL 2021 Philip J. Ball, Cong Lu, Jack Parker-Holder, Stephen Roberts

Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or impractical exploration.

OffCon$^3$: What is state of the art anyway?

1 code implementation27 Jan 2021 Philip J. Ball, Stephen J. Roberts

Two popular approaches to model-free continuous control tasks are SAC and TD3.

Continuous Control

A Study on Efficiency in Continual Learning Inspired by Human Learning

no code implementations28 Oct 2020 Philip J. Ball, Yingzhen Li, Angus Lamb, Cheng Zhang

We study a setting where the pruning phase is given a time budget, and identify connections between iterative pruning and multiple sleep cycles in humans.

Continual Learning

Towards Tractable Optimism in Model-Based Reinforcement Learning

no code implementations21 Jun 2020 Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts

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).

Continuous Control Decision Making +4

Active inference: demystified and compared

1 code implementation24 Sep 2019 Noor Sajid, Philip J. Ball, Thomas Parr, Karl J. Friston

In this paper, we provide: 1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in RL; 2) an explicit discrete-state comparison between active inference and RL on an OpenAI gym baseline.

Atari Games OpenAI Gym +2

The Sensitivity of Counterfactual Fairness to Unmeasured Confounding

1 code implementation1 Jul 2019 Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva

We demonstrate our new sensitivity analysis tools in real-world fairness scenarios to assess the bias arising from confounding.

counterfactual Fairness

Cannot find the paper you are looking for? You can Submit a new open access paper.