Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks · HackerPapers discussions

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks — mentioned by edran

Sat, 12 Aug 2017 00:04:26 GMT

The micromanagement task in StarCraft Broodwar (with TorchCraft) that has been used by a few people already in the past year to do some RL research has been tackled basically only with #units > 1, because getting a balanced 1v1 is possible only with certain combination of units, and it's indeed pointless otherwise. Kiting is maybe a notable exception, but it is also restricted to a relatively small group of unit matchups. See for instance the following papers: - https://arxiv.org/abs/1609.02993 - https://arxiv.org/abs/1702.08887 - https://arxiv.org/abs/1703.10069…

Paper and discussion history. A mention is not an endorsement.

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks — mentioned by chrishare

Fri, 04 Nov 2016 22:23:54 GMT

Very interesting stuff. Allowing researchers to build AIs that operate on either game state or visual data is a great step, IMO. Being able to limit actions-per-minute is also very wise. The excellent BWAPI library for Starcraft Broodwar that is referenced (https://github.com/bwapi/bwapi) provides game state - and was presumably used by Facebook to do their research earlier this year (http://arxiv.org/abs/1609.02993). For mine, the significant new challenges here not present in Go are the partial observability of the game and the limited time window in which decisions need to be made. Even at…

Paper and discussion history. A mention is not an endorsement.

Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks — HN submission

Wed, 14 Sep 2016 13:12:50 GMT

Deep Reinforcement Learning to Play StarCraft

116 points; 50 discussion replies on HN. Paper and source history. A submission is not an endorsement.