Related papers: Time Hopping technique for faster reinforcement le…
Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high…
Hindsight experience replay (HER) accelerates off-policy reinforcement learning algorithms for environments that emit sparse rewards by modifying the goal of the episode post-hoc to be some state achieved during the episode. Because…
This paper has been withdrawn by the author.
In large-scale problems, standard reinforcement learning algorithms suffer from slow learning speed. In this paper, we follow the framework of using subspaces to tackle this problem. We propose a free-energy minimization framework for…
This paper explores how to enhance existing masked time-series modeling by randomly dropping sub-sequence level patches of time series. On this basis, a simple yet effective method named DropPatch is proposed, which has two remarkable…
In this research, we introduce a deep reinforcement learning-based control approach to address the intricate challenge of the robotic pre-grasping phase under microgravity conditions. Leveraging reinforcement learning eliminates the…
In this addendum we introduce the concept of time-inversion referencing. This is an extension of hypertext allowing authors to cite papers that where not yet published (or even not yet written) when they publish a manuscript. We are…
We study a posterior sampling approach to efficient exploration in constrained reinforcement learning. Alternatively to existing algorithms, we propose two simple algorithms that are more efficient statistically, simpler to implement and…
We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique…
Many astrophysical simulations involve extreme dynamic range of timescales around 'special points' in the domain (e.g. black holes, stars, planets, disks, galaxies, shocks, mixing interfaces), where processes on small scales couple strongly…
The generalization ability of machine learning models degrades significantly when the test distribution shifts away from the training distribution. We investigate the problem of training models that are robust to shifts caused by changes in…
Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge…
Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm…
This paper introduces a new method for inverse reinforcement learning in large-scale and high-dimensional state spaces. To avoid solving the computationally expensive reinforcement learning problems in reward learning, we propose a function…
The paper has been withdrawn by the author.
Cold atom traps are at the heart of many quantum applications in science and technology. The preparation and control of atomic clouds involves complex optimization processes, that could be supported and accelerated by machine learning. In…
This paper has been withdrawn by the author.
We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on…
Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…
Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…