A Unity ID allows you to buy and/or subscribe to Unity products and services, shop in the Asset Store and participate in the Unity community.
Separate names with a comma.
it's called "decision requester", you just add it as a new component to your gameobject - i.e. click your agent gameobject, press "add new...
it's a script that is supplied with MLA so you just attach it to your gameobject along with your agent script
looks like you're not requesting a decision/action anywhere, even for heurisitics to work you will need to do so (i.e. attach decision requester...
if 1 side is able to train but the other isn't it sounds like the observations are not quite right, did you base your project on the demos?
simplest method is perhaps removing the manual calling of request decision / environmentstep and using the decision requester component as that...
you mean the link? well it's just on unity's official discord under ai-tools
arrays are 0 indexed so branch of 1 is going to always output 0, so if your 'if' statements are checking for 1 they'll never be true until you...
there is an official discord too
so what makes you say collectobservation isn't doing anything? is it being executed? do you have 2 discrete branches of size 2?
do you have a decision requester component on the agent?
are you sure it's not working or is it just because it's in fixed update time and you're trying to get the exact frame the spacebar was pressed?...
best bet is to end an agent's episode as soon as possible so if they start going the wrong way for some time end their episode and restart them so...
yes, it will still get blocked by anything in the same layer(s) that are set, the tags are for the agent to be able tell the objects apart but the...
if you want it to ignore everything else you need to set the ray layer mask to only detect the layer the "Player Attack" tag objects are on (i.e....
restarting worker[0] usually happens if you press stop in unity while the command line is attempting to start the training (i.e. if you stop unity...
the code looks like it should work ok as far as only jumping when on the ground etc so do you mean it jumps a lot? this is normal, when training...
interesting, it should be set (and greyed out by default, not sure why yours isn't) run in background is important so you can bring the cmd line...
do you have your discrete action space set to size above 1 in the agent behaviour parameters? do you have unity set to run in the background?
override the onepisodebegin function in your script instead public override void OnEpisodeBegin() { ResetAgent(); }
little bit of 2D ragdoll fun - see if you can beat the AI at keeping the ball in the air https://smallg2017.itch.io/bounce-ball [MEDIA]