A definition of continual reinforcement learning
In a standard view of the reinforcement learning problem, an agent's goal is to efficiently
identify a policy that maximizes long-term reward. However, this perspective is based on a …
identify a policy that maximizes long-term reward. However, this perspective is based on a …
Disentangling the causes of plasticity loss in neural networks
Underpinning the past decades of work on the design, initialization, and optimization of
neural networks is a seemingly innocuous assumption: that the network is trained on a\textit …
neural networks is a seemingly innocuous assumption: that the network is trained on a\textit …
Continual learning: Applications and the road forward
Continual learning is a sub-field of machine learning, which aims to allow machine learning
models to continuously learn on new data, by accumulating knowledge without forgetting …
models to continuously learn on new data, by accumulating knowledge without forgetting …
Dynamically masked discriminator for GANs
Abstract Training Generative Adversarial Networks (GANs) remains a challenging problem.
The discriminator trains the generator by learning the distribution of real/generated data …
The discriminator trains the generator by learning the distribution of real/generated data …
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
This study investigates the loss of generalization ability in neural networks, revisiting warm-
starting experiments from Ash & Adams. Our empirical analysis reveals that common …
starting experiments from Ash & Adams. Our empirical analysis reveals that common …
Weight Clipping for Deep Continual and Reinforcement Learning
Many failures in deep continual and reinforcement learning are associated with increasing
magnitudes of the weights, making them hard to change and potentially causing overfitting …
magnitudes of the weights, making them hard to change and potentially causing overfitting …
Data-dependent and Oracle Bounds on Forgetting in Continual Learning
L Friedman, R Meir - arXiv preprint arXiv:2406.09370, 2024 - arxiv.org
In continual learning, knowledge must be preserved and re-used between tasks,
maintaining good transfer to future tasks and minimizing forgetting of previously learned …
maintaining good transfer to future tasks and minimizing forgetting of previously learned …
Harnessing Discrete Representations for Continual Reinforcement Learning
EJ Meyer, A White, MC Machado - 2023 - openreview.net
Reinforcement learning (RL) agents make decisions using nothing but observations from the
environment, and consequently, heavily rely on the representations of those observations …
environment, and consequently, heavily rely on the representations of those observations …
[PDF][PDF] Three Dogmas of Reinforcement Learning
Modern reinforcement learning has been conditioned by at least three dogmas. The first is
the environment spotlight, which refers to our tendency to focus on modeling environments …
the environment spotlight, which refers to our tendency to focus on modeling environments …
[PDF][PDF] Successive Refinement in Continual Learning: A Study on Spatial Representations
Humans' capacity for perpetual learning and adjustment in response to novel circumstances
throughout their lifespan is exceptional. This cognitive aptitude, known as Continual …
throughout their lifespan is exceptional. This cognitive aptitude, known as Continual …