diff --git a/torch_training/bla.py b/torch_training/bla.py index 2dfec096fd854b3d14a4698b67e5be667313c5d1..8b89720d49b164e5603d55bcdd3d24c6d750b3ba 100644 --- a/torch_training/bla.py +++ b/torch_training/bla.py @@ -153,7 +153,9 @@ def main(argv): if demo: eps = 0 # action = agent.act(np.array(obs[a]), eps=eps) + print("before act") action = agent.act(agent_obs[a], eps=eps) + print("after act") action_prob[action] += 1 action_dict.update({a: action}) # Environment step