Publications (13)
One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
Marc Rigter, Bruno Lacerda, Nick Hawes
Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making s…
The Essential Role of Causality in Foundation World Models for Embodied AI
Tarun Gupta, Wenbo Gong, Chao Ma +11
Recent advances in foundation models, especially in large multi-modal models and conversational agents, have ignited interest in the potential of generally capable embodied agents.…
Planning for Risk-Aversion and Expected Value in MDPs
Marc Rigter, Paul Duckworth, Bruno Lacerda +1
Planning in Markov decision processes (MDPs) typically optimises the expected cost. However, optimising the expectation does not consider the risk that for any given run of the MDP…
Reward-Free Curricula for Training Robust World Models
Marc Rigter, Minqi Jiang, Ingmar Posner
There has been a recent surge of interest in developing generally-capable agents that can adapt to new tasks without additional training in the environment. Learning world models f…
RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning
Marc Rigter, Bruno Lacerda, Nick Hawes
Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the en…
World Models via Policy-Guided Trajectory Diffusion
Marc Rigter, Jun Yamada, Ingmar Posner
World models are a powerful tool for developing intelligent agents. By predicting the outcome of a sequence of actions, world models enable policies to be optimised via on-policy r…