protected override float OnEvaluate(AIEnvironment env)
{
// Note: assumes the center is at x=0.
var x = Abs(env.players[env.AiPlayerId(aiId)].position.x);
var edge = env.stage.rightEdge;
var red = edge - redZoneSize;
var yellow = edge - yellowZoneSize;
if (x < yellow)
{
// [0, .1]
return(.1f * x / yellow);
}
else if (x < red)
{
// [.1, .7]
var pct = (x - yellow) / (yellowZoneSize - redZoneSize);
return(.1f + .6f * pct * pct);
}
else
{
// [.7, 1]
return(.7f + .3f * (x - red) / redZoneSize);
}
}
public void Deactivate(AIEnvironment env)
{
if (activeControl != Control.None)
{
inputManager.Release(activeControl);
}
OnDeactivate(env);
}
protected override int OnExecute(AIEnvironment env)
{
if (env.players[env.AiPlayerId(aiId)].position.x < 0)
{
return(Control.Right);
}
else
{
return(Control.Left);
}
}
protected override float OnEvaluate(AIEnvironment env)
{
if (UpdateTimer(env))
{
ChangeDirection(env.threadRandom);
}
if (direction == Direction.Invalid)
{
return(0);
}
return(.1f);
}
/// For each item in `agMask`, add the difference between the new
/// and old utility values. If the net utility is better, we want
/// to replace all matches with the new value.
private void TakeBestStrategy(
int strategyIndex,
Decision[,] existingDecisions,
AIEnvironment env
)
{
var strategy = strategies[strategyIndex];
var utility = strategy.Evaluate(env);
if (utility < .001f)
{
return;
}
uint agMask = strategy.actionGroupMask & ActionGroup.All;
var decision = new Decision(utility, agMask, strategyIndex);
// If I end up needing to support multiple groups per strategy:
// In a loop for each bit of the new decision's mask, look
// at the current best decision for that spot. For each spot
// the current decision occupies but the new one doesn't, find
// the net utility loss by replacing those with the second place
// values and the net utility gain from placing the new decision
// in the slots it needs. If the gain is more than the loss,
// replace it. Don't erase the second place values when moving
// them into first - they may need to replace a future value.
// If the current decision only has one bit set and its utility
// is greater than the second place's utility, even if it is
// also greater than first place's utility, replace second.
int agIndex = LeastBitIndex(agMask);
int aiIndex = strategy.aiId;
// It's ok if this is being written to - if it is, that means
// the result from this thread will not be used and we will get
// reset by `CtlLateUpdate`.
var oldStrategyIndex = prevStrategyIds[aiIndex, agIndex];
if (
oldStrategyIndex != -1 &&
!strategies[oldStrategyIndex]
.CanTransitionTo(strategy.GetType())
)
{
return;
}
var oldUtility = existingDecisions[aiIndex, agIndex].utility;
if (utility > oldUtility)
{
existingDecisions[aiIndex, agIndex] = decision;
}
}
/// Returns true if timer expired.
private bool UpdateTimer(AIEnvironment env)
{
var time = env.time;
if (time > nextChangeTime)
{
var dt = (float)(env.threadRandom.NextDouble() * 24 + 1);
// Use Sqrt to weight this toward the upper range.
nextChangeTime = time + Sqrt(dt);
return(true);
}
return(false);
}
public AIEnvironment(AIEnvironment orig)
{
this.time = orig.time;
this.aiIdMap = orig.aiIdMap;
this.gameSp = orig.gameSp;
this.stageSp = orig.stageSp;
this.playersSp = orig.playersSp;
this.players = new PlayerSnapshot[this.playersSp.Length];
for (var i = 0; i < this.players.Length; i++)
{
this.players[i].attacks = new AttackState[Player.attackCount];
}
}
public void Execute(AIEnvironment env)
{
var c = OnExecute(env);
if (c < Control.None || c >= Control.ArrayLength)
{
c = Control.None;
}
if (c != activeControl)
{
inputManager.Release(activeControl);
}
activeControl = c;
inputManager.Press(c);
}
protected override void OnActivate(AIEnvironment env)
{
var vx = env.players[1].velocity.x;
if (Abs(vx) < .25f)
{
ChangeDirection(env.threadRandom);
}
else if (vx < 0)
{
direction = Direction.Left;
}
else
{
direction = Direction.Right;
}
}
public void Ready(
AIEnvironment env,
IEnumerable <Strategy> strategies
)
{
this.env = env;
this.env2 = new AIEnvironment(env);
this.strategies = Shuffle(strategies.ToList());
this.nextBlockStart = this.strategies.Count;
var aiCount = env.AiCount();
int threads = threadResults.Length;
for (int i = 0; i < threads; i++)
{
threadResults[i] = new Decision[aiCount, ActionGroup.Count];
}
this.strategyIdsRead = new int[aiCount, ActionGroup.Count];
this.strategyIdsWrite = new int[aiCount, ActionGroup.Count];
this.prevStrategyIds = new int[aiCount, ActionGroup.Count];
this.startEvent = new EventWaitHandle(false, EventResetMode.ManualReset);
this.ctlEvent = new EventWaitHandle(false, EventResetMode.ManualReset);
Thread.MemoryBarrier();
evalThreads
= Enumerable.Range(0, threads)
.Select(id => {
var t = new Thread(EvalThreadMain);
t.IsBackground = true;
t.Start(id);
return(t);
})
.ToArray();
controlThread = new Thread(ControlThreadMain);
controlThread.IsBackground = true;
controlThread.Priority = ThreadPriority.BelowNormal;
controlThread.Start();
}
/// Returns true if there is a strategy to execute, false if not.
private bool ActivateStrategy(
int newSid,
ref int oldSid,
AIEnvironment env
)
{
bool hasNewStrategy = newSid >= 0;
if (newSid == oldSid)
{
return(hasNewStrategy);
}
if (oldSid > -1)
{
this.strategies[oldSid].Deactivate(env);
}
if (newSid > -1)
{
this.strategies[newSid].Activate(env);
}
oldSid = newSid;
return(hasNewStrategy);
}
// --
public float Evaluate(AIEnvironment env)
{
return(UnityEngine.Mathf.Clamp01(OnEvaluate(env)));
}
/// The basic idea is this: the threads all block on `startEvent`.
/// When the event is set, they start processing slices of the array,
/// guaranteed not to overlap via interlocked operations, and evenly
/// distributed over all computer players by shuffling the array
/// at the start.
private void EvalThreadMain(object threadIdObj)
{
startEvent.WaitOne();
int threadId = (int)threadIdObj;
Interlocked.Increment(ref activeThreads);
AIEnvironment env = this.env;
// These don't change (for now).
var strategyCount = this.strategies.Count;
var threadCount = this.evalThreads.Length;
var blockSize = this.blockSize;
try {
while (true)
{
var blockEnd = Interlocked.Add(ref nextBlockStart, blockSize);
var blockStart = blockEnd - blockSize;
if (blockStart >= strategyCount)
{
// Flush all the results from this thread to memory.
Thread.MemoryBarrier();
startEvent.Reset();
// For the last thread, we need to merge the individual
// results into the main strategy IDs array before
// setting the active thread count to 0.
int currentCount;
bool merged = false;
do
{
currentCount = Volatile.Read(ref activeThreads);
if (currentCount == 1 && !merged)
{
// TODO: Someone may do this twice.
// Get rid of this by sharding AIs over threads.
MergeDecisions();
merged = true;
}
} while (
Interlocked.CompareExchange(
ref activeThreads,
currentCount - 1,
currentCount
) != currentCount
);
try {
startEvent.WaitOne();
if (!Volatile.Read(ref running))
{
"EndThread({0}/{1})".LogF(currentCount, threadCount);
return;
}
} catch (Exception e) {
"{0}".ErrorF(e);
// If we let an exception go between the
// decrement and increment, the counter
// will stop being accurate. This way, it will
// always be set to zero whether a thread
// terminates or they all are just paused.
// TODO: If startEvent fails, that messes up the
// synchronization entirely. How to handle this?
return;
}
ResetDecisionArray(threadResults[threadId]);
Interlocked.Increment(ref activeThreads);
env = Volatile.Read(ref this.env);
continue;
}
if (blockEnd > strategyCount)
{
blockEnd = strategyCount;
}
// FIXME! Move thread specific environment out -
// AIEnvironment is immutable only during processing!
SetupEnvForThread(env, evalThreadRandom[threadId]);
for (int i = blockStart; i < blockEnd; i++)
{
TakeBestStrategy(i, threadResults[threadId], env);
}
}
} catch (Exception e) {
"{0}".ErrorF(e);
Interlocked.Decrement(ref activeThreads);
return;
}
}
protected override int OnExecute(AIEnvironment env)
{
return(direction.AsControl());
}
/// Must be thread safe. protected abstract float OnEvaluate(AIEnvironment env);
/// Returns the desired control. protected abstract int OnExecute(AIEnvironment env);
protected virtual void OnDeactivate(AIEnvironment env)
{
}
public void Activate(AIEnvironment env)
{
this.activeControl = Control.None;
OnActivate(env);
}
/// Set non-thread-safe variables to thread-local copies before passing
/// the environment to a strategy.
private void SetupEnvForThread(AIEnvironment env, Random threadRandom)
{
env.threadRandom = threadRandom;
}