0ad/source/simulation2
wraitii 5473393e30 Add an interface for Reinforcement Learning.
Implement a simple HTTP server to start games, receive the gamestate and
pass commands to the simulation.
This is mainly intended for training reinforcement learning agents in 0
AD. As such, a python client and a small example are included.

This option can be enabled using the -rl-interface flag.

Patch by: irishninja
Reviewed By: wraitii, Itms
Fixes #5548

Differential Revision: https://code.wildfiregames.com/D2199
This was SVN commit r23917.
2020-08-01 10:52:59 +00:00
..
components Allow selectable component to overwrite shape of displayed selection from footprint 2020-07-26 18:26:20 +00:00
docs Replace deprecated jsval with JS::Value. 2017-08-28 10:27:36 +00:00
helpers Fix building on GCC 10, fixes #5709, #5756. 2020-06-30 10:24:00 +00:00
scripting Improve the warning message for FromJSValue<CColor> when trying to convert a non-object to CColor. 2020-06-01 16:09:28 +00:00
serialization RangeManager: Grid for 2D array, enum cleanups. 2020-06-13 09:05:40 +00:00
system Add an interface for Reinforcement Learning. 2020-08-01 10:52:59 +00:00
tests RangeManager: Grid for 2D array, enum cleanups. 2020-06-13 09:05:40 +00:00
MessageTypes.h UnitMotion - Send messages to UnitAI when obstructed, to allow stopping early when walking and avoiding pathfinding lag. 2019-07-22 18:07:24 +00:00
Simulation2.cpp Use victory conditions json's in Atlas 2020-07-18 17:39:59 +00:00
Simulation2.h Use victory conditions json's in Atlas 2020-07-18 17:39:59 +00:00
TypeList.h Add a C++ interface for CCmpAttack. 2020-04-21 21:44:05 +00:00