BouncerLearning:
normalize: true
beta: 0.0
max_steps: 5.0e5
num_layers: 2
hidden_units: 64
max_steps: 5.0e4
init_entcoef: 0.05
beta: 1.0e-2
hidden_units: 256
summary_freq: 2000
time_horizon: 64
StrikerLearning:
learning_rate: 1e-3
time_horizon: 128
GoalieLearning:
buffer_init_steps: 1000
num_layers: 1
buffer_size: 500000
init_entcoef: 0.01
hidden_units: 128
memory_size: 256
init_entcoef: 0.1
summary_freq: 1000
gamma: 0.99
batch_size: 64
buffer_size: 1024