diff --git a/run.py b/run.py index aaa4babd34b20e53273ff76a4c7cb74579e75c99..d610faba273f00404f1b660f7eb75501ddafc12e 100644 --- a/run.py +++ b/run.py @@ -137,9 +137,9 @@ while True: action = agent_last_action[agent] nb_hit += 1 else: - action = policy.act(observation[agent], eps=0.0) - #if observation[agent][26] == 1: - # action = RailEnvActions.STOP_MOVING + action = policy.act(observation[agent], eps=0.01) + if observation[agent][26] == 1: + action = RailEnvActions.STOP_MOVING action_dict[agent] = action