Data aggregation techniques can significantly improve vision-based policy learning within a
training environment, eg, learning to drive in a specific simulation condition. However, as on …

Unlike humans, who are capable of continual learning over their lifetimes, artificial neural
networks have long been known to suffer from a phenomenon known as catastrophic …

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that
is\textit {agnostic} to the timescale of changes in the distribution of experiences, does not …

Reinforcement learning algorithms can solve dynamic decision-making and optimal control
problems. With continuous-valued state and input variables, reinforcement learning …

In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual
learning in RL agents faced with environments that are changing continuously over time at …

Experience replay buffer improves sample efficiency and training stabilization for recent
deep reinforcement learning (DRL) methods. However, for the first-in-first-out (FIFO) …

Abstract Model-based reinforcement learning (RL) algorithms can be used to derive optimal
control laws for nonlinear dynamic systems. With continuous-valued state and input …

In this paper we consider the problem of how to balance exploration and exploitation in
deep reinforcement learning (DRL). We propose a generative method called double replay …

In off-policy reinforcement learning, an agent collects transition data (aka experience tuples)
from the environment and stores them in a replay buffer for the incoming parameter updates …