no code implementations • 6 Feb 2024 • Tarun Gupta, Wenbo Gong, Chao Ma, Nick Pawlowski, Agrin Hilmkil, Meyer Scetbon, Marc Rigter, Ade Famoti, Ashley Juan Llorens, Jianfeng Gao, Stefan Bauer, Danica Kragic, Bernhard Schölkopf, Cheng Zhang
The study of causality lends itself to the construction of veridical world models, which are crucial for accurately predicting the outcomes of possible interactions.
1 code implementation • 13 Dec 2023 • Marc Rigter, Jun Yamada, Ingmar Posner
Our results demonstrate that PolyGRAD outperforms state-of-the-art baselines in terms of trajectory prediction error for short trajectories, with the exception of autoregressive diffusion.
no code implementations • 7 Nov 2023 • Jun Yamada, Marc Rigter, Jack Collins, Ingmar Posner
The teacher world model then supervises a student world model that takes the domain-randomised image observations as input.
1 code implementation • 15 Jun 2023 • Marc Rigter, Bruno Lacerda, Nick Hawes
In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time.
1 code implementation • 15 Jun 2023 • Marc Rigter, Minqi Jiang, Ingmar Posner
We consider robustness in terms of minimax regret over all environment instantiations and show that the minimax regret can be connected to minimising the maximum error in the world model across environment instances.
no code implementations • 2 Apr 2023 • Marc Rigter
The over-arching goal of this thesis is to contribute to developing algorithms that mitigate both sources of uncertainty in sequential decision-making problems.
1 code implementation • NeurIPS 2023 • Marc Rigter, Bruno Lacerda, Nick Hawes
Our model-based approach is risk-averse to both epistemic and aleatoric uncertainty.
2 code implementations • 26 Apr 2022 • Marc Rigter, Bruno Lacerda, Nick Hawes
Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy optimisation within that model, have emerged as a promising approach to this problem.
no code implementations • 14 Mar 2022 • Marc Rigter, Danial Dervovic, Parisa Hassanzadeh, Jason Long, Parisa Zehtabi, Daniele Magazzeni
To improve the scalability of our approach to a greater number of task classes, we present an approximation based on state abstraction.
1 code implementation • 25 Oct 2021 • Marc Rigter, Paul Duckworth, Bruno Lacerda, Nick Hawes
This motivates us to propose a lexicographic approach which minimises the expected cost subject to the constraint that the CVaR of the total cost is optimal.
no code implementations • NeurIPS 2021 • Marc Rigter, Bruno Lacerda, Nick Hawes
In this work, we address risk-averse Bayes-adaptive reinforcement learning.
no code implementations • 8 Dec 2020 • Marc Rigter, Bruno Lacerda, Nick Hawes
We propose a dynamic programming algorithm that utilises the regret Bellman equation, and show that it optimises minimax regret exactly for UMDPs with independent uncertainties.