# Selected Papers

This page contains a subset of the papers that were mentioned or discussed during the workshop.

Thank you to Esra'a Saleh for compiling the list.

Monday

Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration

The Dynamics of Active Categorical Perception in an Evolved Model Agent

Towards Continual Reinforcement Learning: A Review and Perspectives

The Difficulty of Passive Learning in Deep Reinforcement Learning

Online Real-Time Recurrent Learning Using Sparse Connections and Selective Learning

Tuesday

Neural Collapse: A Review on Modelling Principles and Generalization

The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces

Value-Aware Loss Function for Model-based Reinforcement Learning

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

On the role of planning in model-based deep reinforcement learning

Meta-Gradient Reinforcement Learning with an Objective Discovered Online

Learning to Prioritize Planning Updates in Model-based Reinforcement Learning

Natural Value Approximators: Learning when to Trust Past Estimates

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability

The Large Learning Rate Phase of Deep Learning: The Catapult Mechanism

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality

Interference and Generalization in Temporal Difference Learning

Wednesday

Training Uncertainty-Aware Classifiers with Conformalized Deep Learning

The Quest for a Common Model of the Intelligent Decision Maker

Mark's "CHILD" 1997 paper - CHILD: A First Step Towards Continual Learning

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning

Interlude: A Mechanistic Interpretability Analysis of Grokking â Neel Nanda

Gradient-based Optimization is Not Necessary for Generalization in Neural Networks

Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning

A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern

Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier

Thursday

Continual Learning In Environments With Polynomial Mixing Times

Passive setting: Optimizing for the Future in Non-Stationary MDPs

Active setting: Off-Policy Evaluation for Action-Dependent Non-stationary Environments

Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning

References for Shapley values. [Chapter in the Interpretable ML book] and [The Many Shapley Values for Model Explanation]