3 commits

Author	SHA1	Message	Date
wraitii	df18102e96	Add an 'Evaluate' RL endpoint, intended for dynamic game balancing ... This adds a new endpoint to the RL interface for evaluating custom JavaScript. When combined with the ability to create arbitrary modifiers, this provides the required functionality for exploring quantitative game balancing. Patch By: irishninja Fixes #5981 Differential Revision: https://code.wildfiregames.com/D3479 This was SVN commit r24962.	2021-02-28 12:16:32 +00:00
wraitii	42b068d9c9	RL: Update template paths & remove debug-print. ... debug-print was removed in 992d740a58, templates were changed in b57abe806c Patch by: irishninja Differential Revision: https://code.wildfiregames.com/D3502 This was SVN commit r24816.	2021-02-01 14:53:40 +00:00
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