[f'fD_dynamics'],
lambda x: torch.mean(F.relu(x - dxudmax)),
weight=args.Q_con_fdu,
name='dist_influence_ub')
constraints += [
disturbances_max_influence_lb, disturbances_max_influence_ub
]
##########################################
########## OPTIMIZE SOLUTION ############
##########################################
model = Problem(objectives, constraints, components).to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=args.lr)
visualizer = VisualizerOpen(dataset,
dynamics_model,
args.verbosity,
args.savedir,
training_visuals=args.train_visuals,
trace_movie=args.trace_movie)
# simulator = OpenLoopSimulator(model=model, dataset=dataset, eval_sim=not args.skip_eval_sim)
simulator = MHOpenLoopSimulator(model=model,
dataset=dataset,
eval_sim=not args.skip_eval_sim)
trainer = Trainer(model,
dataset,
optimizer,
logger=logger,
visualizer=visualizer,
simulator=simulator,
epochs=args.epochs,
eval_metric=args.eval_metric,
patience=args.patience,
simulator = OpenLoopSimulator(model=model, dataset=dataset, eval_sim=not args.skip_eval_sim)
optimizer = torch.optim.AdamW(model.parameters(), lr=args.lr)
trainer = Trainer(
model,
dataset,
optimizer,
logger=logger,
simulator=simulator,
epochs=args.epochs,
eval_metric=args.eval_metric,
patience=args.patience,
warmup=args.warmup,
)
best_model = trainer.train()
best_outputs = trainer.evaluate(best_model)
visualizer = VisualizerOpen(
dataset,
dynamics_model,
args.verbosity,
args.savedir,
training_visuals=args.train_visuals,
trace_movie=args.trace_movie,
)
plots = visualizer.eval(best_outputs)
logger.log_artifacts(plots)
logger.clean_up()