Anti-exploration by random network distillation
Despite the success of Random Network Distillation (RND) in various domains, it was shown
as not discriminative enough to be used as an uncertainty estimator for penalizing out-of …
as not discriminative enough to be used as an uncertainty estimator for penalizing out-of …
Revisiting the minimalist approach to offline reinforcement learning
Recent years have witnessed significant advancements in offline reinforcement learning
(RL), resulting in the development of numerous algorithms with varying degrees of …
(RL), resulting in the development of numerous algorithms with varying degrees of …
Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Katakomba: tools and benchmarks for data-driven NetHack
NetHack is known as the frontier of reinforcement learning research where learning-based
methods still need to catch up to rule-based solutions. One of the promising directions for a …
methods still need to catch up to rule-based solutions. One of the promising directions for a …
Distilling LLMs' Decomposition Abilities into Compact Language Models
D Tarasov, K Shridhar - arXiv preprint arXiv:2402.01812, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated proficiency in their reasoning abilities,
yet their large size presents scalability challenges and limits any further customization. In …
yet their large size presents scalability challenges and limits any further customization. In …
The role of deep learning regularizations on actors in offline rl
Deep learning regularization techniques, such as dropout, layer normalization, or weight
decay, are widely adopted in the construction of modern artificial neural networks, often …
decay, are widely adopted in the construction of modern artificial neural networks, often …
Judgmentally adjusted Q-values based on Q-ensemble for offline reinforcement learning
W Liu, S Xiang, T Zhang, Y Han, X Guo… - Neural Computing and …, 2024 - Springer
Recent advancements in offline reinforcement learning (offline RL) have leveraged the Q-
ensemble approach to derive optimal policies from static datasets collected in the past. By …
ensemble approach to derive optimal policies from static datasets collected in the past. By …
基于表征学习的离线强化学习方法研究综述
王雪松， 王荣荣， 程玉虎 - 自动化学报, 2024 - aas.net.cn
强化学习通过智能体与环境在线交互来学习最优策略, 近年来已成为解决复杂环境下感知决策
问题的重要手段. 然而, 在线收集数据的方式可能会引发安全, 时间或成本等问题 …
问题的重要手段. 然而, 在线收集数据的方式可能会引发安全, 时间或成本等问题 …
Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning
Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets
without interacting with the environment. A common challenge is handling multi-modal …
without interacting with the environment. A common challenge is handling multi-modal …
An approach to improve agent learning via guaranteeing goal reaching in all episodes
P Osinenko, G Yaremenko, G Malaniya… - arXiv preprint arXiv …, 2024 - arxiv.org
Reinforcement learning is commonly concerned with problems of maximizing accumulated
rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the …
rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the …