6 papers
Finding the Time to Think: Learning Planning Budgets in Real-Time RL
Aneesh Muppidi, Firas Darwish, Dylan Cope +2
Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's dec…
JAX-Based Batched AC Power Flow for GPU Acceleration and AI Ecosystem Integration
Yihong Zhou, Dylan Cope, Jakob Foerster +1
Coordinating growing grid flexibility under uncertainty is becoming increasingly important for efficient and reliable power-system operation. A core computational requirement is th…
Evolution Strategies at the Hyperscale
Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque +17
Evolution Strategies (ES) is a class of powerful black-box optimisation methods that are highly parallelisable and can handle non-differentiable and noisy objectives. However, naï…
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Yohan Mathew, Ollie Matthews, Robert McCarthy +4
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to…
Decoding Communications with Partial Information
Dylan Cope, Peter McBurney
Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempt…
Training Neural Networks for Modularity aids Interpretability
Satvik Golechha, Dylan Cope, Nandi Schoots
An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models t…