mlabonne

# Get data
minerl.data.download(directory='data', environment='MineRLTreechop-v0')
data = minerl.data.make("MineRLTreechop-v0", data_dir='data', num_workers=2)

# Model
model = CNN((3, 64, 64), 7).cuda()
optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)
criterion = nn.CrossEntropyLoss()

# Training loop

mlabonne

class CNN(nn.Module):
    def __init__(self, input_shape, output_dim):
        super().__init__()
        n_input_channels = input_shape[0]
        self.cnn = nn.Sequential(
            nn.Conv2d(n_input_channels, 32, kernel_size=8, stride=4),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.Conv2d(32, 64, kernel_size=4, stride=2),
            nn.BatchNorm2d(64),

mlabonne

script = []
script += [''] * 20 
script += ['forward'] * 5
script += ['attack'] * 61
script += ['camera:[-10,0]'] * 7  # Look up
script += ['attack'] * 240
script += ['jump']
script += ['forward'] * 10        # Jump forward
script += ['camera:[-10,0]'] * 2  # Look up
script += ['attack'] * 150

mlabonne

# Define the sequence of actions
script = ['forward'] * 5 + [''] * 40

env = gym.make('MineRLObtainDiamond-v0')
env = Recorder(env, './video', fps=60)
env.seed(21)
obs = env.reset()

for action in script:
    # Get the action space (dict of possible actions)

mlabonne

env = gym.make('MineRLObtainDiamond-v0')
env.seed(21)

mlabonne

class CountSolutions(cp_model.CpSolverSolutionCallback):
    """Count the number of solutions."""

    def __init__(self):
        cp_model.CpSolverSolutionCallback.__init__(self)
        self.__solution_count = 0

    def on_solution_callback(self):
        self.__solution_count += 1

mlabonne

# Solve problem
status = solver.Solve(model)

# If an optimal solution has been found, print results
if status == cp_model.OPTIMAL:
    print('================= Solution =================')
    print(f'Solved in {solver.WallTime():.2f} milliseconds')
    print()
    print(f'Optimal value = {3*solver.Value(bread)+10*solver.Value(meat)+26*solver.Value(beer)} popularity')
    print('Food:')

mlabonne

# 3. Objective
model.Maximize(3  * bread
             + 10 * meat
             + 26 * beer)

mlabonne

# 2. Constraints
model.Add(1 * bread
        + 3 * meat 
        + 7 * beer <= capacity)

mlabonne

# Instantiate model and solver
model = cp_model.CpModel()
solver = cp_model.CpSolver()

# 1. Variables
capacity = 19
bread = model.NewIntVar(0, capacity, 'bread')
meat  = model.NewIntVar(0, capacity, 'meat')
beer  = model.NewIntVar(0, capacity, 'beer')