In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …

The uncanny ability of over-parameterised neural networks to generalise well has been
explained using various" simplicity biases". These theories postulate that neural networks …

We provide quantitative bounds measuring the $ L^ 2$ difference in function space between
the trajectory of a finite-width network trained on finitely many samples from the idealized …

Deep neural networks provide Reinforcement Learning (RL) powerful function
approximators to address large-scale decision-making problems. However, these …

Cross-domain offline reinforcement learning leverages source domain data with diverse
transition dynamics to alleviate the data requirement for the target domain. However, simply …

We propose a novel value approximation method, namely “E igensubspace R egularized C
ritic (ERC)” for deep reinforcement learning (RL). ERC is motivated by an analysis of the …

Reinforcement learning is time-consuming for complex tasks due to the need for large
amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym …

Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a
potentially discontinuous value function, and generalizing well to new observations. In this …

Periodic activation functions, often referred to as learned Fourier features have been widely
demonstrated to improve sample efficiency and stability in a variety of deep RL algorithms …

Deep neural networks can struggle to learn continually in the face of non-stationarity. This
phenomenon is known as loss of plasticity. In this paper, we identify underlying principles …