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 …
Plastic: Improving input and label plasticity for sample efficient reinforcement learning
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 …
in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms …
Deep reinforcement learning with plasticity injection
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 …
learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the …
Improving language plasticity via pretraining with active forgetting
Pretrained language models (PLMs) are today the primary model for natural language
processing. Despite their impressive downstream performance, it can be difficult to apply …
processing. Despite their impressive downstream performance, it can be difficult to apply …
Maintaining plasticity via regenerative regularization
In continual learning, plasticity refers to the ability of an agent to quickly adapt to new
information. Neural networks are known to lose plasticity when processing non-stationary …
information. Neural networks are known to lose plasticity when processing non-stationary …
Drm: Mastering visual reinforcement learning through dormant ratio minimization
Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite
its progress, current algorithms are still unsatisfactory in virtually every aspect of the …
its progress, current algorithms are still unsatisfactory in virtually every aspect of the …
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 as computationally constrained reinforcement learning
An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …
Small batch deep reinforcement learning
J Obando Ceron, M Bellemare… - Advances in Neural …, 2024 - proceedings.neurips.cc
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 …
specifies how many transitions to sample for each gradient update. Although critical to the …
COOM: a game benchmark for continual reinforcement learning
The advancement of continual reinforcement learning (RL) has been facing various
obstacles, including standardized metrics and evaluation protocols, demanding …
obstacles, including standardized metrics and evaluation protocols, demanding …