[change] Reduce max_steps for PushBlock and Bouncer
summary_freq: 20000
PushBlock:
max_steps: 1.5e7
max_steps: 2e6
init_entcoef: 0.05
hidden_units: 256
summary_freq: 60000
Bouncer:
normalize: true
max_steps: 7.0e6
max_steps: 4.0e6
max_steps: 2.0e6
batch_size: 128
buffer_size: 2048
beta: 1.0e-2