12 accepted papers
Humans excel at learning abstract patterns across different sequences, filtering out irrelevant details, and transferring these generalized concepts to new sequences. In contrast, many sequence learning models lack the ability to abstract, which leads to memory inefficiency and poor transfer. We int…
Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspective that challenges the prevailing view: rather than being inscrutable, neural networks exhibit patterns in their raw po…
To solve control problems via model-based reasoning or planning, an agent needs to know how its actions affect the state of the world. The actions an agent has at its disposal often change the state of the environment in systematic ways. However, existing techniques for world modelling do not guaran…
In reinforcement learning (RL), simplicity is typically quantified on an action-by-action basis -- but this timescale ignores temporal regularities, like repetitions, often present in sequential strategies. We therefore propose an RL algorithm that learns to solve tasks with sequences of actions tha…
One of the most important and challenging application areas for complex machine learning methods is to predict, characterize and model rich, multi-dimensional, neural data. Recent advances in neural recording techniques have made it possible to monitor the activity of a large number of neurons acros…
We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL). A common approach is to learn off-policy, using data sampled from a replay buffer. However, messages received in the past may not accurately reflect the current communication policy of each agent, and…
Distributional reinforcement learning (RL) – in which agents learn about all the possible long-term consequences of their actions, and not just the expected value – is of great recent interest. One of the most important affordances of a distributional view is facilitating a modern, measured, approac…
Recent theoretical and experimental results suggest that the dopamine system implements distributional temporal difference backups, allowing learning of the entire distributions of the long-run values of states rather than just their expected values. However, the distributional codes explored so far…
Monte-Carlo Tree Search (MCTS) is one of the most-widely used methodsfor planning, and has powered many recent advances in artificialintelligence. In MCTS, one typically performs computations(i.e., simulations) to collect statistics about the possible futureconsequences of actions, and then chooses…
Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects' behavior and then studying differences between them in the associated parameter space. However, these models often fit behavior more poorly than recurrent neural net…
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance bottleneck. One potential remedy is to augment the network with…
Neuroscience studies of human decision-making abilities commonly involve subjects completing a decision-making task while BOLD signals are recorded using fMRI. Hypotheses are tested about which brain regions mediate the effect of past experience, such as rewards, on future actions. One standard appr…