num_layers: 2
SmallWallJump:
max_steps: 3e7
max_steps: 5e6
hidden_units: 256
summary_freq: 20000
time_horizon: 128
BigWallJump:
max_steps: 2e7
batch_size: 128
buffer_size: 2048
beta: 5.0e-3
normalize: false