drl-supply-chain-rllib-sim.py

config = ddpg.DEFAULT_CONFIG.copy()
config["actor_hiddens"] = [512, 512] 
config["critic_hiddens"] = [512, 512]
config["gamma"] = 0.95
config["timesteps_per_iteration"] = 1000
config["target_network_update_freq"] = 5
config["buffer_size"] = 10000
    
trainer = ddpg.DDPGTrainer(config=config, env=SimpleSupplyChain)
for i in range(n_iterations):
   result = trainer.train()
   print(pretty_print(result))
  
#> Achieved profit: 9238.2