Plasticity, the ability of a neural network to quickly change its predictions in response to new
information, is essential for the adaptability and robustness of deep reinforcement learning …

Offline Reinforcement Learning (RL) aims to learn policies from previously collected
datasets without exploring the environment. Directly applying off-policy algorithms to offline …

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount
of offline data for complex decision-making tasks. Due to the distribution shift issue, current …

Abstract In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly
in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms …

A growing body of evidence suggests that neural networks employed in deep reinforcement
learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the …

The reinforcement learning (RL) problem is rife with sources of non-stationarity, making it a
notoriously difficult problem domain for the application of neural networks. We identify a …

In many contexts, simpler models are preferable to more complex models and the control of
this model complexity is the goal for many methods in machine learning such as …

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in
JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and …

In value-based deep reinforcement learning with replay memories, the batch size parameter
specifies how many transitions to sample for each gradient update. Although critical to the …

We propose a new class of deep reinforcement learning (RL) algorithms that model latent
representations in hyperbolic space. Sequential decision-making requires reasoning about …