On Improving Deep Reinforcement Learning for POMDPs [article]

Pengfei Zhu, Xin Li, Pascal Poupart, Guanghui Miao
<span title="2018-05-08">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architecture called Action-specific Deep Recurrent Q-Network (ADRQN) to enhance learning performance in partially observable domains. Actions are encoded by a fully connected layer and
more &raquo; ... pled with a convolutional observation to form an action-observation pair. The time series of action-observation pairs are then integrated by an LSTM layer that learns latent states based on which a fully connected layer computes Q-values as in conventional Deep Q-Networks (DQNs). We demonstrate the effectiveness of our new architecture in several partially observable domains, including flickering Atari games.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.06309v2">arXiv:1804.06309v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/edqab5pgmvgwfjkd3qwevs5drm">fatcat:edqab5pgmvgwfjkd3qwevs5drm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824235919/https://arxiv.org/pdf/1804.06309v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/36/83/3683bec9df63f27952c08c4ebb7fcd7d15de4378.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.06309v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>