Refactoring: Intdocued fix_agents function.

At each step we first check for possible malfunctions.
THen we apply them and do all the agent steps
At the end we look at what agents should be fixed. This lead so to:

Current malfunction value says how many step calls are necessary till agent can move again

e.g. malfunction = 2, we have to call step() twice untill the agent can move again.

Code cleanup

examples/introduction_flatland_2_1.py

@@ -27,7 +27,7 @@ from flatland.utils.rendertools import RenderTool, AgentRenderVariant
 
 width = 16*7  # With of map
 height = 9*7  # Height of map
-nr_trains = 10  # Number of trains that have an assigned task in the env
+nr_trains = 20  # Number of trains that have an assigned task in the env
 cities_in_map = 20  # Number of cities where agents can start or end
 seed = 14  # Random seed
 grid_distribution_of_cities = False  # Type of city distribution, if False cities are randomly placed
@@ -58,7 +58,7 @@ schedule_generator = sparse_schedule_generator(speed_ration_map)
 # We can furthermore pass stochastic data to the RailEnv constructor which will allow for stochastic malfunctions
 # during an episode.
 
-stochastic_data = {'malfunction_rate': 1000,  # Rate of malfunction occurence of single agent
+stochastic_data = {'malfunction_rate': 5,  # Rate of malfunction occurence of single agent
                    'min_duration': 3,  # Minimal duration of malfunction
                    'max_duration': 20  # Max duration of malfunction
                    }

flatland/envs/rail_env.py

@@ -427,7 +427,6 @@ class RailEnv(Environment):
 
         """
         if self.np_random.rand() < self._malfunction_prob(rate, len(self.active_agents)):
-            print("Malfunction")
             # Select only from agents that are not done yet
             breaking_agent_idx = self.np_random.choice(self.active_agents)
             breaking_agent = self.agents[breaking_agent_idx]

tests/test_utils.py

@@ -121,7 +121,7 @@ def run_replay_config(env: RailEnv, test_configs: List[ReplayConfig], rendering:
                 agent.malfunction_data['moving_before_malfunction'] = agent.moving
                 agent.malfunction_data['fixed'] = False
             _assert(a, agent.malfunction_data['malfunction'], replay.malfunction, 'malfunction')
-        print(step, agent.moving, agent.malfunction_data['fixed'], agent.malfunction_data['malfunction'])
+        print(step)
         _, rewards_dict, _, info_dict = env.step(action_dict)
         if rendering:
             renderer.render_env(show=True, show_observations=True)