English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep reinforcement learning (DRL) has great potential for acquiring theoptimal action in complex environments such as games and robot control.However, it is difficult to analyze the decision-making of the agent, i.e., thereasons it selects the action acquired by learning. In this work, we proposeMask-Attention A3C (Mask A3C), which introduces an attention mechanism intoAsynchronous Advantage Actor-Critic (A3C), which is an actor-critic-based DRLmethod, and can analyze the decision-making of an agent in DRL. A3C consists ofa feature extractor that extracts features from an image, a policy branch thatoutputs the policy, and a value branch that outputs the state value. In thismethod, we focus on the policy and value branches and introduce an attentionmechanism into them. The attention mechanism applies a mask processing to thefeature maps of each branch using mask-attention that expresses the judgmentreason for the policy and state value with a heat map. We visualizedmask-attention maps for games on the Atari 2600 and found we could easilyanalyze the reasons behind an agent's decision-making in various game tasks.Furthermore, experimental results showed that the agent could achieve a higherperformance by introducing the attention mechanism.

Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning