Since blizzcon guests are able to play vs alphastar from the blizzard arcade this year, I decided to give it my best shot. For those of you who don't know me, I am a mid-GM protoss player on the NA server (best finish is rank 50). There were two 'difficulties' of alphastar that were playing; basic and advanced. Advanced being the full power AlphaStar agent that was being tested on the EU ladder. J. Allen Brack said 'if you try this, you will not win'.
Game 1 (Vs AlphaStar Advanced Zerg):
For my first game against AlphaStar I decided to do an off-meta build that I used to use a lot, a glaive adept timing followed by a DT drop. AlphaStar took a bit of damage from my build, but managed to significantly delay my third base with a pack of zerglings. The follow up roach ravager bust completely ran me over, showcasing AlphaStar's excellent mechanics and macro.
AlphaStar has - at the time of writing - had two major releases unveiled in January and November of 2019. The core design of how AlphaStar is built and learns is fairly consistent across both. AlphaStar Math, Computer Science and Physics Winter Camps are unique opportunities for interested and talented students to improve their skills during winter break. Students are guided and trained by utilizing national and international competitions in a fun and challenging environment. With Alpha Star Electric, you can always count on high quality workmanship and that’s simply because nothing less is acceptable to us! Entrust us with your residential, commercial, industrial or forestry electrical projects. AlphaStar also had a global view rather than being limited by the in-game camera. Furthermore, while there was a cap on the number of actions over a five-second window, AlphaStar was free to allocate its action quota unevenly across the window in order to launch superhuman bursts of activity at critical moments.
Game 2 (Vs AlphaStar Advanced Zerg):
The second game I decided to do a printf style cannon rush on new repugnancy with a double robo immortal follow up. I am not particularly experienced with this build and was hoping AlphaStar would self desctruct. AlphaStar instead expanded all over the map and managed to build a large ravager ling queen army to defeat my immortals by the time i lost my main.
Game 3 (Vs AlphaStar Advanced Protoss):
AlphaStar did what at first looked like a normal pvp opener, but made 2 zealots out of its first two gates. I decided to attempt to punish this with some stalker pressure, only to discover that alphastar had used the gas it saved by making zealots to rush a large amount of phoenixes. Without proper tools to deal with phoenix harass my economy was slowly picked apart and I died to a the first big attack.
Alphastar Academy
Game 4: (Vs AlphaStar Advanced Protoss)
AlphaStar opened with a low ground gateway with a fast expand (in pvp, what?) and I decided to punish it with 3 gate robo all in. AlphaStar rushed an immortal and a warp prism and displayed absolutely god-tier micro to hold my push.
Game 5: (Vs AlphaStar Advanced Protoss:
I attempted to do a mostly standard build, I opened with stalker sentry and went into blink. AlphaStar did more or less the same build as me and we both expanded. My blink finished and I decided to go pressure. AlphaStar then moved out with blink and a warp prism, and went I tried to fight it did BOTH BLINK MICRO AND PRISM MICRO AT THE SAME TIME. I was completely unable to fight its army and was quickly defeated.
Game 6: (Vs AlphaStar Advanced Protoss):
Finally, I threw in the towel, this bot needed taste defeat. So I decided to cannon rush again (this time in a matchup that I am a bit more familiar with cannon rushing in). AlphaStar saw my cannon rush and at first did a pretty solid defense, pulling probes to prevent cannons from going up and to block me from walling in a cannon. Eventually I got a cannon up, but the huge amount of probes that alphastar pulled to the low ground would eventually kill it. This is when AlphaStar made its first and last mistake, it had pulled WAY too many probes into the enclosed area by my pylons, and I quickly placed two pylons to trap nearly all of its probes. With no probes mining, AlphaStar died to a few zealots. Sweet victory, take that J. Allen Brack!
Bonus: At the end of game 6, AlphaStar had a single probe left and a pylon. When I found the pylon with my units AlphaStar did the GG spray before being eliminated. The deepmind devs said they didn't tell AlphaStar to do it. Here's a video of AlphaStar's final moments where you can see the GG spray:
Source: Original link
- All AlphaStar final PvZ games summarized
General opening and game plan: Standard Stargate opening with probescout and 2 adepts Probescout doesn’t check for 3rd or where lings are going 2 adepts shade in to deal damage 4min 3rd after 2nd gate in wall Build oracles for harassment and holding 3rd Robo continuously harass with adepts shading into mineral lines ~5 oracles…
- How to Beat AlphaStar: From the Perspective of a Grandmaster Player and Data Scientist
To preface this discussion, I want to state that despite the title of this post, I still think AlphaStar is going to beat most, if not all, of us. The people at Deepmind are brilliant and the demonstration in Janurary was nothing short of remarkable. Yet, perhaps you, the high gold/low diamond zerg player, will…
- 'Toxic' draft turned into one of the most fun games I've ever played :)
Map: Sky Temple our team first 3 picks Butcher Nova Nazeebo In the beginning, there was some toxicity the leader tried to ask about who to ban so the first pick could choose whatever they wanted, but I think they were AFK. ( it happens to us all the queues are long lol )…
© Post 'I played (and beat) AlphaStar Advanced At Blizzcon, here is how the games went.' for game StarCraft.
Top 10 Most Anticipated Video Games of 2020
Alphastar
2020 will have something to satisfy classic and modern gamers alike. To be eligible for the list, the game must be confirmed for 2020, or there should be good reason to expect its release in that year. Therefore, upcoming games with a mere announcement and no discernible release date will not be included.
Top 15 NEW Games of 2020 [FIRST HALF]
2020 has a ton to look forward to...in the video gaming world. Here are fifteen games we're looking forward to in the first half of 2020.
AlphaStar is a computer program by DeepMind that plays the video game StarCraft II. It was unveiled to the public by name in January 2019. In a significant milestone for artificial intelligence, AlphaStar attained Grandmaster status in August 2019.
Background[edit]
Games created for humans are considered to have external validity as benchmarks of progress in artificial intelligence. IBM's chess-playing Deep Blue (1997) and DeepMind's AlphaGo (2016) were considered major milestones; some argue that StarCraft would also be a major milestone, due to StarCraft's 'real-time play, partial observability, no single dominant strategy, complex rules that make it hard to build a fast forward model, and a particularly large and varied action space.'[1] Though difficult, StarCraft may still be tractable with current technology because 'its rules are known and the world is discrete with only a few types of objects'.[2]
StarCraft II is a popular fast-paced online real-time strategy game by Blizzard Entertainment.[3][4]
History[edit]
DeepMind Technologies was founded in the UK in 2010. As early as 2011, founder Demis Hassabis called StarCraft 'the next step up' after games like Go.[5] DeepMind became a Google subsidiary in 2014, after demonstrating self-learning bots with superhuman ability at a variety of Atari 2600 games. In February 2015, computer scientist Zachary Mason predicted Deepmind's research 'leads to StarCraft in five or ten years'.[6] In March 2016, following AlphaGo's victory over a world champion Go player, Hassabis publicly mulled building an AI for StarCraft, citing it as a strategic game with incomplete information where (unlike Go) much of the 'board' is invisible.[7][8] A formal collaboration was announced at BlizzCon in November 2016, alongside a plan to release an open development environment for bots in Q1 of 2017.[9]
By 2017, DeepMind was experimenting with feeding StarCraft data into its software. In August 2017, DeepMind and Blizzard released development tools to assist in bot development, as well as data from 65,000 past games. At the time, computer scientist and StarCraft tournament manager David Churchill guessed it would take five years for a bot to beat a human, but made the caveat that AlphaGo had beaten expectations. In Wired, tech journalist Tom Simonite stated, 'No one expects the robot to win anytime soon. But when it does, it will be a far greater achievement than DeepMind's conquest of Go.'[10]
On 19 December 2018, DeepMind's bot defeated 'a top professional player', Grzegorz 'MaNa' Komincz, 5-0. DeepMind announced the bot, named 'AlphaStar', on 24 January 2019. A journalist at Ars Technica and others argued that AlphaStar still had unfair advantages: 'AlphaStar has the ability to make its clicks with surgical precision using an API, whereas human players are constrained by the mechanical limits of computer mice'. AlphaStar also had a global view rather than being limited by the in-game camera. Furthermore, while there was a cap on the number of actions over a five-second window, AlphaStar was free to allocate its action quota unevenly across the window in order to launch superhuman bursts of activity at critical moments. DeepMind quickly retrained AlphaStar under more realistic constraints, and then lost a rematch with Komincz.[11] Starting in July 2019, the new, constrained version of AlphaStar anonymously competed against players who 'opted in' on the public 1v1 European multiplayer ladder.[12] By the end of August 2019, AlphaStar had attained 'grandmaster level', ranking among the top 0.2 percent of human players.[13]
Alphastar Starcraft
Algorithms[edit]
Unlike AlphaZero, AlphaStar initially learns to imitate the moves of the best players in its database of human vs. human games; this step is necessary to solve what DeepMind's Dave Silver calls 'the exploration problem': discovering new strategies would otherwise be like finding a 'needle in a haystack'. Agents then play each other and deploy reinforcement learning. These main agents also learn by playing against suboptimal 'exploiter agents' whose purpose is to expose weaknesses in the main agents.[14][15]
Alphastar Ai
Reactions[edit]
After his 5-0 defeat in December 2018, Komincz stated 'I wasn't expecting the AI to be that good'.[16]
Stuart Russell assessed that AlphaStar's 2018 victory required 'a fair amount of problem-specific effort' and that general-purpose methods were 'not quite ready for StarCraft'.[2]
An article in Wired UK judged AlphaStar's new constraints, adopted for the July 2019 matches, to be 'fair' this time around.[17]StarCraft pro Raza 'RazerBlader' Sekha stated AlphaStar was 'impressive' but had its quirks, succumbing in one game to an unorthodox army composition made up of only air units. The UK's top player, Joshua 'RiSky' Hayward, expressed some disappointment, saying AlphaStar 'often didn't make the most efficient, strategic decisions'.[14] Pro Diego 'Kelazhur' Schwimer called AlphaStar's play 'unimaginably unusual; it really makes you question how much of StarCraft's diverse possibilities pro players have really explored'.[13] AlphaStar's opponents often did not realize they were playing a bot.[18]
Alphastar
Ian Sample of The Guardian called AlphaStar a 'landmark achievement' for the field of artificial intelligence.[19] Churchill stated that he had previously seen bots that master one or two elements of StarCraft, but that AlphaStar was the first that can handle the game in its entirety.[3]Gary Marcus expressed his continuing skepticism about deep learning, stating: 'So far the field has struggled to take techniques like this out of the laboratory and game environments and into the real world, and I don't immediately see this result as progress in that direction'.[14] AI researcher Jon Dodge was surprised by AlphaStar, stating he did not expect such a 'superhuman' performance for 'another couple of years'; in contrast, Churchill states 'StarCraft is nowhere near being 'solved', and AlphaStar is not yet even close to playing at a world champion level'.[4]
Legacy[edit]
DeepMind argues that insights from AlphaStar might benefit robots, self-driving cars and virtual assistants, which need to operate with 'imperfectly observed information'. Silver has indicated his lab 'may rest at this point', rather than try to substantially improve AlphaStar.[14] Silver himself argues that 'AlphaStar has become the first AI system to reach the top tier of human performance in any professionally played e-sport on the full unrestricted game under professionally approved conditions... Ever since computers cracked Go, chess and poker, the game of StarCraft has emerged, essentially by consensus from the community, as the next grand challenge for AI.'[19]
Alphastarav.com
Computer scientist Noel Sharkey argues, disapprovingly, that 'military analysts will certainly be eyeing the successful AlphaStar real-time strategies as a clear example of the advantages of AI for battlefield planning'.[19] In contrast, Silver argues: 'To say that this has any kind of military use is saying no more than to say an AI for chess could be used to lead to military applications'.[14]
See also[edit]
References[edit]
- ^Arulkumaran, Kai; Antoine, Cully; Togelius, Julian (July 2019). 'AlphaStar: An evolutionary computation perspective'. Proceedings of the Genetic and Evolutionary Computation Conference Companion: 314–5. arXiv:1902.01724. doi:10.1145/3319619.3321894.
- ^ abRussell, Stuart (8 October 2019). 'Chapter 2: Intelligence in Humans and Machines'. Human Compatible: Artificial Intelligence and the Problem of Control (Hardcover ed.). Viking. ISBN978-0-525-55861-3.
- ^ abDaley, Jason (30 October 2019). 'A.I. Mastered Backgammon, Chess and Go. Now It Takes On StarCraft II'. Smithsonian Magazine. Retrieved 26 February 2020.
- ^ abGaristo, Dan (30 October 2019). 'Google AI beats top human players at strategy game StarCraft II'. Nature. doi:10.1038/d41586-019-03298-6.
- ^Cheng, Jonathan (22 April 2016). 'Computers That Crush Humans at Games Might Have Met Their Match: 'StarCraft''. Wall Street Journal. Retrieved 26 February 2020.
- ^Gibbs, Samuel (27 January 2014). 'Google buys UK artificial intelligence startup Deepmind for £400m'. The Guardian. Retrieved 26 February 2020.
- ^Byford, Sam (10 March 2016). 'DeepMind founder Demis Hassabis on how AI will shape the future'. The Verge. Retrieved 26 February 2020.
- ^'Google's Artificial Intelligence Project May Start Playing Video Games'. Fortune. Retrieved 26 February 2020.
- ^Byford, Sam (4 November 2016). 'Google DeepMind's next gaming challenge: can AI beat StarCraft II?'. The Verge. Retrieved 26 February 2020.
- ^'Google DeepMind AI Declares Galactic War on StarCraft'. Wired. 9 August 2017. Retrieved 26 February 2020.
- ^Lee, Timothy B. (30 January 2019). 'An AI crushed two human pros at StarCraft—but it wasn't a fair fight'. Ars Technica. Retrieved 26 February 2020.
- ^Amadeo, Ron (11 July 2019). 'DeepMind AI is secretly lurking on the public StarCraft II 1v1 ladder'. Ars Technica. Retrieved 26 February 2020.
- ^ abStatt, Nick (30 October 2019). 'DeepMind's StarCraft 2 AI is now better than 99.8 percent of all human players'. The Verge. Retrieved 26 February 2020.
- ^ abcdeKelion, Leo (30 October 2019). 'DeepMind claims landmark moment for AI in esports'. BBC News. Retrieved 26 February 2020.
- ^Vinyals, Oriol; Babuschkin, Igor; Czarnecki, Wojciech M.; et al. (30 October 2019). 'Grandmaster level in StarCraft II using multi-agent reinforcement learning'. Nature. 575 (7782): 350–354. Bibcode:2019Natur.575..350V. doi:10.1038/s41586-019-1724-z. PMID31666705.
- ^Heaven, Douglas (21 August 2019). 'Mind meld: Artificial intelligence is improving the way humans think'. New Scientist. Retrieved 26 February 2020.
- ^Lee, Alex (30 October 2019). 'DeepMind has finally thrashed humans at StarCraft for real'. Wired UK. Retrieved 26 February 2020.
- ^'DeepMind claims breakthrough as AI masters StarCraft II game'. Financial Times. 2019. Retrieved 26 February 2020.
- ^ abcSample, Ian (30 October 2019). 'AI becomes grandmaster in 'fiendishly complex' StarCraft II'. The Guardian. Retrieved 26 February 2020.
External links[edit]
- DeepMind StarCraft II Demonstration on YouTube