This adresses issue #264

Fixes the examples

examples/complex_rail_benchmark.py

@@ -24,28 +24,11 @@ def run_benchmark():
     action_dict = dict()
     action_prob = [0] * 4
 
-    def max_lt(seq, val):
-        """
-        Return greatest item in seq for which item < val applies.
-        None is returned if seq was empty or all items in seq were >= val.
-        """
-
-        idx = len(seq) - 1
-        while idx >= 0:
-            if seq[idx] < val and seq[idx] >= 0:
-                return seq[idx]
-            idx -= 1
-        return None
-
     for trials in range(1, n_trials + 1):
 
         # Reset environment
         obs, info = env.reset()
 
-        for a in range(env.get_num_agents()):
-            norm = max(1, max_lt(obs[a], np.inf))
-            obs[a] = np.clip(np.array(obs[a]) / norm, -1, 1)
-
         # Run episode
         for step in range(100):
             # Action
@@ -56,9 +39,6 @@ def run_benchmark():
 
             # Environment step
             next_obs, all_rewards, done, _ = env.step(action_dict)
-            for a in range(env.get_num_agents()):
-                norm = max(1, max_lt(next_obs[a], np.inf))
-                next_obs[a] = np.clip(np.array(next_obs[a]) / norm, -1, 1)
 
             if done['__all__']:
                 break

examples/custom_observation_example_02_SingleAgentNavigationObs.py

@@ -35,7 +35,11 @@ class SingleAgentNavigationObs(ObservationBuilder):
     def get(self, handle: int = 0) -> List[int]:
         agent = self.env.agents[handle]
 
-        possible_transitions = self.env.rail.get_transitions(*agent.position, agent.direction)
+        if agent.position:
+            possible_transitions = self.env.rail.get_transitions(*agent.position, agent.direction)
+        else:
+            possible_transitions = self.env.rail.get_transitions(*agent.initial_position, agent.direction)
+
         num_transitions = np.count_nonzero(possible_transitions)
 
         # Start from the current orientation, and see which transitions are available;

examples/debugging_example_DELETE.py

-import random
-import time
-from typing import List
-
-import numpy as np
-
-from flatland.core.env_observation_builder import ObservationBuilder
-from flatland.core.grid.grid4_utils import get_new_position
-from flatland.envs.rail_env import RailEnv
-from flatland.envs.rail_generators import complex_rail_generator
-from flatland.envs.schedule_generators import complex_schedule_generator
-from flatland.utils.rendertools import RenderTool
-
-random.seed(1)
-np.random.seed(1)
-
-
-class SingleAgentNavigationObs(ObservationBuilder):
-    """
-    We build a representation vector with 3 binary components, indicating which of the 3 available directions
-    for each agent (Left, Forward, Right) lead to the shortest path to its target.
-    E.g., if taking the Left branch (if available) is the shortest route to the agent's target, the observation vector
-    will be [1, 0, 0].
-    """
-
-    def __init__(self):
-        super().__init__()
-
-    def reset(self):
-        pass
-
-    def get(self, handle: int = 0) -> List[int]:
-        agent = self.env.agents[handle]
-
-        possible_transitions = self.env.rail.get_transitions(*agent.position, agent.direction)
-        num_transitions = np.count_nonzero(possible_transitions)
-
-        # Start from the current orientation, and see which transitions are available;
-        # organize them as [left, forward, right], relative to the current orientation
-        # If only one transition is possible, the forward branch is aligned with it.
-        if num_transitions == 1:
-            observation = [0, 1, 0]
-        else:
-            min_distances = []
-            for direction in [(agent.direction + i) % 4 for i in range(-1, 2)]:
-                if possible_transitions[direction]:
-                    new_position = get_new_position(agent.position, direction)
-                    min_distances.append(self.env.distance_map.get()[handle, new_position[0], new_position[1], direction])
-                else:
-                    min_distances.append(np.inf)
-
-            observation = [0, 0, 0]
-            observation[np.argmin(min_distances)] = 1
-
-        return observation
-
-
-env = RailEnv(width=14,
-              height=14,
-              rail_generator=complex_rail_generator(nr_start_goal=10, nr_extra=1, min_dist=5, max_dist=99999, seed=1),
-              schedule_generator=complex_schedule_generator(),
-              number_of_agents=2,
-              obs_builder_object=SingleAgentNavigationObs())
-
-obs, info = env.reset()
-env_renderer = RenderTool(env, gl="PILSVG")
-env_renderer.render_env(show=True, frames=True, show_observations=False)
-for step in range(100):
-    actions = {}
-    for i in range(len(obs)):
-        actions[i] = np.argmax(obs[i]) + 1
-
-    if step % 5 == 0:
-        print("Agent halts")
-        actions[0] = 4  # Halt
-
-    obs, all_rewards, done, _ = env.step(actions)
-    if env.agents[0].malfunction_data['malfunction'] > 0:
-        print("Agent 0 broken-ness: ", env.agents[0].malfunction_data['malfunction'])
-
-    env_renderer.render_env(show=True, frames=True, show_observations=False)
-    time.sleep(0.5)
-    if done["__all__"]:
-        break
-env_renderer.close_window()