A grid-world navigation agent trained across browser GPU workers. Each round, workers run Q-learning episodes in parallel on the GPU, then the coordinator merges their Q-table updates. Watch the value landscape and greedy policy evolve in real time.
Not started
rl-agent @ waiting…idle
UnexploredLearningLearnedWallStartGoal
Round
0 / 0
Goal rate
—
Avg steps
—
Episodes
0
Workers0
--:--:--warppool rl-agent · v0.3.1
Distributed Q-learning. Workers run episodes on GPU; coordinator merges Q-tables each round.