diff --git a/flatland/envs/distance_map.py b/flatland/envs/distance_map.py index c6e73b0bdbe752b8d5df9c4a0697bb621e5276ec..2bc1a5117794959cca82d2edad821cb629397f78 100644 --- a/flatland/envs/distance_map.py +++ b/flatland/envs/distance_map.py @@ -55,7 +55,6 @@ class DistanceMap: self.env_width = rail.width def _compute(self, agents: List[EnvAgent], rail: GridTransitionMap): - print("computing distance map") self.agents_previous_computation = self.agents self.distance_map = np.inf * np.ones(shape=(len(agents), self.env_height, diff --git a/flatland/envs/rail_env.py b/flatland/envs/rail_env.py index 2543fc9180298d2b2b6be07a8a82d7730218b037..cda0dee972395be0aa5e29e6695337e40f0fdc52 100644 --- a/flatland/envs/rail_env.py +++ b/flatland/envs/rail_env.py @@ -459,6 +459,7 @@ class RailEnv(Environment): agent.status = RailAgentStatus.ACTIVE agent.position = agent.initial_position self.rewards_dict[i_agent] += self.step_penalty * agent.speed_data['speed'] + print(self.rewards_dict[i_agent]) return else: # TODO: Here we need to check for the departure time in future releases with full schedules diff --git a/tests/test_flaltland_rail_agent_status.py b/tests/test_flaltland_rail_agent_status.py index ec7635ba05c7d7aec3964f9964d1341baef8e96a..099ccce6462f21217df0bd03abacc4716e52993b 100644 --- a/tests/test_flaltland_rail_agent_status.py +++ b/tests/test_flaltland_rail_agent_status.py @@ -50,7 +50,7 @@ def test_initial_status(): reward=env.step_penalty * 0.5, # running at speed 0.5 ), Replay( - position=(3, 8), + position=(3, 9), direction=Grid4TransitionsEnum.WEST, status=RailAgentStatus.ACTIVE, action=RailEnvActions.MOVE_FORWARD, @@ -64,7 +64,7 @@ def test_initial_status(): reward=env.step_penalty * 0.5, # running at speed 0.5 ), Replay( - position=(3, 7), + position=(3, 8), direction=Grid4TransitionsEnum.WEST, status=RailAgentStatus.ACTIVE, action=RailEnvActions.MOVE_FORWARD, @@ -79,7 +79,7 @@ def test_initial_status(): status=RailAgentStatus.ACTIVE ), Replay( - position=(3, 6), + position=(3, 7), direction=Grid4TransitionsEnum.WEST, action=RailEnvActions.MOVE_RIGHT, reward=env.step_penalty * 0.5, # wrong action is corrected to forward without penalty! @@ -93,7 +93,7 @@ def test_initial_status(): status=RailAgentStatus.ACTIVE ), Replay( - position=(3, 5), + position=(3, 6), direction=Grid4TransitionsEnum.WEST, action=None, reward=env.global_reward, # already done