diff --git a/flatland/envs/rail_env.py b/flatland/envs/rail_env.py index b4a56a8d241a4a1d6706ff67bad6030ce619ebf0..abc8a738355dbf19bf08cf6a55f088166537dec1 100644 --- a/flatland/envs/rail_env.py +++ b/flatland/envs/rail_env.py @@ -231,7 +231,7 @@ class RailEnv(Environment): self.rewards_dict[iAgent] += stop_penalty if not agent.moving and not (action == RailEnvActions.DO_NOTHING or action == RailEnvActions.STOP_MOVING): - # Only allow agent to start moving by pressing forward. + # Allow agent to start with any forward or direction action agent.moving = True self.rewards_dict[iAgent] += start_penalty @@ -270,6 +270,7 @@ class RailEnv(Environment): else: # TODO: an invalid action was chosen after entering the cell. The agent cannot move. self.rewards_dict[iAgent] += invalid_action_penalty + self.rewards_dict[iAgent] += step_penalty * agent.speed_data['speed'] agent.moving = False self.rewards_dict[iAgent] += stop_penalty @@ -277,6 +278,7 @@ class RailEnv(Environment): else: # TODO: an invalid action was chosen after entering the cell. The agent cannot move. self.rewards_dict[iAgent] += invalid_action_penalty + self.rewards_dict[iAgent] += step_penalty * agent.speed_data['speed'] agent.moving = False self.rewards_dict[iAgent] += stop_penalty