6 papers
Redistribution-based Cost Inference Improves Sparse Safe Offline RL
Ebenezer Gelo, Geraud Nangue Tasse, Steven James +1
Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback: a binary signal at the first u…
Unsupervised Hierarchical Skill Discovery
Damion Harvey, Geraud Nangue Tasse, Benjamin Rosman +2
We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectori…
Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
Geraud Nangue Tasse, Matthew Riemer, Benjamin Rosman +1
Recent success in developing increasingly general purpose agents based on sequence models has led to increased focus on the problem of deploying computationally limited agents with…
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
Devon Jarvis, Richard Klein, Benjamin Rosman +1
In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Cur…
Revisiting the Role of Relearning in Semantic Dementia
Devon Jarvis, Verena Klar, Richard Klein +2
Patients with semantic dementia (SD) present with remarkably consistent atrophy of neurons in the anterior temporal lobe and behavioural impairments, such as graded loss of categor…
Compositional Instruction Following with Language Models and Reinforcement Learning
Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan +4
Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while simultaneously learning multiple language-conditioned ta…