201–210 of 242 posts
so this is what Grimes latest song is about?
> All the lyrical evidence that Grimes’ new song ‘Player of Games’ is about ex Elon Musk > Grimes seemingly makes multiple, thinly veiled references to Musk in the song https://www.independent.co.uk/arts-entertainment/music/news/...
Earlier quoted context omitted.
PSA: The "Culture" novels by Iain M Banks are fantastic and can be read in any order. "Player of Games" was the 1st one I read and still probably my favorite.
I keep hearing recommendations for the Culture books so I tried reading it recently and it just didn't work for me -- I gave up on it halfway through, which is rare for me.
If you are interested in this, I maintain a list of boardgame-solving related research at https://github.com/captn3m0/boardgame-research , with sections for specific games. This looks really interesting. It would be a good project to test this against a general card-playing framework to easily test it on a variety of imperfect-information games based on playing cards.
Imperfect information games will always have a luck element that gives casual players an edge. That's basically the appeal of card games over board games.
Earlier quoted context omitted.
I tried my hand once or twice at (re-)implementing board games [0], so that I could run some common "AI" algorithms on the game trees. What tripped me up every time is that most board games have a lot of "if this happens, there is this specific rule that applies". Even relatively simple games (like Homeworlds) are pretty hard to nail down perfectly due to all the special cases. Do you, or somebody else, have any reco…
> What tripped me up every time is that most board games have a lot of "if this happens, there is this specific rule that applies". Even relatively simple games (like Homeworlds) are pretty hard to nail down perfectly due to all the special cases. The key is to build a data-driven state machine, rather than writing logic with a bunch of 'if' statements.
Earlier quoted context omitted.
My personal experience was the opposite. I'm currently trying different approaches for building a Bomberman AI for the Bomberland competition that was discussed here on HN a few weeks ago. "IMPALA with 1 learner takes only around 10 hours to reach the same performance that A3C approaches after 7.5 days." says the paper, but I can run A3C on a cheap CPU-only server but to get that IMPALA timing, I need to spend a lot…
Hm not an expert in this, but would something with a world model help, rather than depending on stochastic random action choices? It seems like it should be possible to learn that a frame sequence where you've been next to a bomb for 6 ticks is rapidly decreasing your expected score, and that your score would be significantly better if you weren't in line with the bomb pretty soon.
The classifier has on average 90% accuracy which seems good. I then use the likelihood predicted by this classifier to compute the weight with which I want to train each action and if I want to train it positively (by pulling its likelihood of being chosen up) or negatively (pushing the likelihood of that action down).
However, what this model cannot correctly represent is the fact that whether or not a given situation will turn out to be good or bad in the long term is highly dependent on how you play. So if I train this with replay data, I will score the situations in relation to how well those (outdated) AIs could take advantage of them.
Next up, I'll try to fix this issue by introducing a graph-like stochastic structure. The basic idea is that I encode "from this state S if I take action A, then I can reach state T with P percent likelihood" into yet another neural network. If I then identify a state which is really beneficial in the sense that I can reliably convert it into an advantage, then I can use this graph to back-propagate that knowledge so that I get "from this state S, action A takes me to state T, then action B takes me to state U, and U is great".
That should allow me to train with historical data to identify which transitions are possible, and then I can combine that with realtime data about the desirability of each state. So basically I'd do A* pathfinding over the graph of possible states to identify which actions are needed to bring me from my current situation into the closest "I will surely win" situation. Except that the graph is memorized by an AI because the real state-space is huge: 15x15 fields with 6 units + 5 environment states => roughly 11^(15*15) states
This is a great result, but you can see that it's more of a theoretical case because of this: "converging to perfect play as available computation time and approximation capacity increases." That is true for pretty much all current deep reinforcement learning algorithms. The practical question is: How much computation do you need to get useful results? Alpha Go Zero is impressive mathematics, but who is willing to sp…
> That is true for pretty much all current deep reinforcement learning algorithms. Is that true? I was unaware that PPO, SAC, DQN, Impala, MuZero/AlphaZero etc would all automatically Just Work™ for hidden information games. Straight MCTS-inspired algorithms seem like they'd fail for reasons discussed in the paper, and while PPO/Impala work reasonably well in DoTA2/SC2, it's not obvious they'd converge to perfect pla…
If I remember correctly, the DeepMind x UCL RL Lecture Series proves the underlying Bellman equation in this video: https://www.youtube.com/watch?v=zSOMeug_i_M
As for "hidden information" games, I thought the trick was to concatenate the current state with all past states and treat that as the new state, thereby making it an MDP.
A bit of googling shows that there is a General Game Playing AI community with their own Game Description Language. I never really encountered them before, and the DeepMind paper does not cite them, either.
Earlier quoted context omitted.
It does, but IMO it's probably worth reading The Player of Games or Use of Weapons before it anyway. With the exception of perhaps Surface Detail, none of the Culture books rely on any others. Consider Phlebas gives a good view of The Culture from "outside" (the perspective of the Idrians) but is quite slow.
I mean, Player of Games has a pretty slow start too. I love that book, but the initial pacing is IMO its biggest flaw. I know Use of Weapons doesn't depend on any of the other books for its plot, but is it a decent intro to the setting? If it is, that's where I'd recommend starting.
My favorite by far is Excession but I don't know that I'd start there. I think the payoff of getting a story from the perspective of the Minds is better appreciated after you've heard about them and their capabilities from a distance in the preceding books.
My pick would be to start with Player of Games. That's the one that was a page turner for me nearly from the jump.
It would be awesome to have two interacting communities: AI experts building open source general game playing engines, and gaming fans writing pluggable rule specifications and UIs for popular games. A bit of googling shows that there is a General Game Playing AI community with their own Game Description Language. I never really encountered them before, and the DeepMind paper does not cite them, either.