58 citations · 394 across the 35 of their papers we have counts for
8 papers · 1 filter
Attention: Marginal Probability is All You Need?
Ryan Singh, Christopher L. Buckley
Attention mechanisms are a central property of cognitive systems allowing them to selectively deploy cognitive resources in a flexible manner. Attention has been long studied in th…
RL with KL penalties is better viewed as Bayesian inference
Tomasz Korbak, Ethan Perez, Christopher L Buckley
Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such…
Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control
Beren Millidge, Anil Seth, Christopher Buckley
The exploration-exploitation trade-off is central to the description of adaptive behaviour in fields ranging from machine learning, to biology, to economics. While many approaches…
Control as Hybrid Inference
Alexander Tschantz, Beren Millidge, Anil K. Seth +1
The field of reinforcement learning can be split into model-based and model-free methods. Here, we unify these approaches by casting model-free policy optimisation as amortised var…
Reinforcement Learning as Iterative and Amortised Inference
Beren Millidge, Alexander Tschantz, Anil K Seth +1
There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and…
Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
Beren Millidge, Alexander Tschantz, Christopher L. Buckley
Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. However, backprop is often criticised fo…