News for hackers. Stuff that matters.
Re:Google Research Football: A Novel Reinforcement Learning ... by gwern on Saturday June 08, 2019 @09:16PM (#20136337)
Should be much cheaper to run despite being a physics simulation:

"The Football Engine is written in highly optimized C++ code, allowing it to be run on off-the-shelf machines, both with GPU and without GPU-based rendering enabled. This allows it to reach a performance of approximately 25 million steps per day on a single hexa-core machine."

Also has some features geared towards generalization, and benchmarking:

"With the Football Benchmarks, we propose a set of benchmark problems for RL research based on the Football Engine. The goal in these benchmarks is to play a “standard” game of football against a fixed rule-based opponent that was hand-engineered for this purpose. We provide three versions: the Football Easy Benchmark, the Football Medium Benchmark, and the Football Hard Benchmark, which only differ in the strength of the opponent. "

"As training agents for the full Football Benchmarks can be challenging, we also provide Football Academy, a diverse set of scenarios of varying difficulty. This allows researchers to get the ball rolling on new research ideas, allows testing of high-level concepts (such as passing), and provides a foundation to investigate curriculum learning research ideas, where agents learn from progressively harder scenarios."

So, as compared to SC2/Dota, you can train much faster, with good baselines to benchmark or compete again, and already built-in support for curriculum learning. SC2/Dota weren't designed for RL, so they're just harder to work with in RL - SC2 has a curriculum which was added on afterwards, for example (the minigames), but Dota2 still doesn't.

Soccer is also more popular than either SC2/DoTA2 as well, so that may be a draw for researchers. More interesting to work on something you like and already know about.

Dunno if all of that together is enough to make it a worthwhile testbed, but it's not obviously worthless or redundant.

Re:Google Research Football: A Novel Reinforcement Learning ... by FartyMcFarter on Sunday June 09, 2019 @04:02AM (#20137863)
> This allows it to reach a performance of approximately 25 million steps per day on a single hexa-core machine."

That is 24 steps per second per thread (or 48 per core).

This doesn't seem that impressive: much more complex games run at that frame rate? FIFA games from the 90s don't look much worse and certainly achieved those frame rates on much older hardware.

Re:Google Research Football: A Novel Reinforcement Learning ... by gwern on Sunday June 09, 2019 @09:58AM (#20139217)
Most of them aren't necessarily trying for realistic physics simulations (they're games, not simulations).