Classic control

Lunar Lander

Thruster control under gravity; evolution tunes landing policies from sparse episodes.

Recordings

Archived weight sets

Training clips

Ensemble evaluations

Learning progress

LunarLander-v3-new-aux4347

LunarLander-v3-new-aux41323

LunarLander-v301302

LunarLander-v3simple314

LunarLander-v3simple2273

LunarLander-v3simple3304

LunarLander-v3simple3 · 2340

adaptive blend306

adaptive standard238

adaptive uniform295

cauchy blend308

cauchy multiparent301

cauchy sbx301

cauchy standard301

gaussian blend306

gaussian sbx238

gaussian standard238

gaussian uniform295

polynomial blend294

polynomial sbx210

polynomial uniform294

standard blend307

standard multiparent295

standard sbx295

standard standard295

standard uniform279

run 17764337

run 7340280

Every logged run as its own mini-curve, best reward per generation; the number shown is that run's final best.

Behavior-map coverage for the best run: the share of the novelty descriptor grid reached as evolution proceeds. 100% = the entire map explored.

Fitness across generations

Each dot represents a training clip: x = filename generation, y = filename fitness (integer-truncated mean training reward). This scatter plot pools recordings without session grouping or per-session traces; dots may overlap and do not form a continuous learning curve.

Each point is one recorded generation from one run; filename fitness is a mean training value, not the return of the clip itself. Points across runs are separate sessions pooled together — the plot is a scatter, not one continuous learning curve.

Featured recording

videos_reward_253_run_70_kFN6_seed_40_7340_20250516_074845_998460-episode-0.mp4

filename fitness 253 · episode 0 · generation 70

Clips by kind

training

ensemble

None archived for this environment.

episode

None archived for this environment.