按年被提到
20162016 · 1 次2026
强化学习与智能体›博弈与游戏 AI·arXiv:1609.05521 · cs.AI

Playing FPS Games with Deep Reinforcement Learning

Guillaume Lample, Devendra Singh Chaplot · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-09-21 · 最近 2018-01-17
2不同的人
2活跃月份
2讨论串
99被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Typically, deep reinforcement learning methods only utilize visual input for training. We present a method to augment these models to exploit game feature information such as the presence of enemies or items, during the training phase. Our model is trained to simultaneously learn these features along with minimizing a Q-learning objective, which is shown to dramatically improve the training speed and performance of our agent. Our architecture is also modularized to allow different models to be independently trained for different phases of the game. We show that the proposed architecture substantially outperforms built-in AI agents of the game as well as humans in deathmatch scenarios.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论rayuela · 2016-09

“Not end-to-end learning. They've included a lot of apriori information into their models to significantly constrain the search space. Maybe I'm being a little too harsh in my opinions, but with this work coming out of CMU I was expecting a little more.”

Playing FPS Video Games with Deep Reinforcement Learning原评论 ↗
讨论串评论spdustin · 2016-09

“I'm anxious to see if the sorts of networks that learned how to play Atari games could be taught to okay slither.io in the same way. I was interested in learning more about the sort of pathfinding challenges slither.io presents (safest path to large food reward with moving obstacles) and started to peel apart some JavaScript "bots" and realized they're do…”

Playing FPS Video Games with Deep Reinforcement Learning原评论 ↗
讨论串评论mountaineer22 · 2016-09

“So, can the AI bots play each other in Deathmatch? Could that then be used as additional training sets?”

Playing FPS Video Games with Deep Reinforcement Learning原评论 ↗
被提交为 story · 2 次