Merge branch 'flatland-3-updates' into 'flatland3-pettingzoo'

# Conflicts:
#   flatland/contrib/interface/flatland_env.py
#   flatland/contrib/requirements_training.txt
#   tests/test_pettingzoo_interface.py

.gitignore

@@ -119,3 +119,5 @@ test_save.dat
 .visualizations
 
 playground/
+**/tmp
+**/TEMP
\ No newline at end of file

.gitlab-ci.yml

@@ -10,6 +10,7 @@ image: themattrix/tox
 ## - AWS_SECRET_ACCESS_KEY
 
 stages:
+    - build_wheel
     - tests
     - integration_testing
     - profiling
@@ -149,4 +150,18 @@ test_conda_setup:
     script:
         - xvfb-run bash getting_started/getting_started.sh
 
-
+build_wheel:
+    image: "python:3.7-slim"
+    stage: build_wheel
+    before_script:
+        - apt update
+        - apt install -y make
+        - pip install -r requirements_dev.txt
+    script:
+        - make dist
+        - export WHEEL_NAME="$( find dist -name 'flatland_rl*.whl' )"
+        - mv "${WHEEL_NAME}" "${WHEEL_NAME/-py2.py3-/-py3-}"
+    artifacts:
+        paths:
+            - dist/flatland_rl*.whl
+        expire_in: 2 mos

README.md

@@ -5,20 +5,22 @@
 
 <p style="text-align:center">
 <img alt="repository" src="https://gitlab.aicrowd.com/flatland/flatland/badges/master/pipeline.svg">
-<img alt="discord" src="https://gitlab.aicrowd.com/flatland/flatland/badges/master/coverage.svg">
+<img alt="coverage" src="https://gitlab.aicrowd.com/flatland/flatland/badges/master/coverage.svg">
 </p>
 
 Flatland is a open-source toolkit for developing and comparing Multi Agent Reinforcement Learning algorithms in little (or ridiculously large!) gridworlds.
 
 [The official documentation](http://flatland.aicrowd.com/) contains full details about the environment and problem statement
 
-Flatland is tested with Python 3.6 and 3.7 on modern versions of macOS, Linux and Windows. You may encounter problems with graphical rendering if you use WSL. Your [contribution is welcome](https://flatland.aicrowd.com/misc/contributing.html) if you can help with this!  
+Flatland is tested with Python 3.6, 3.7 and 3.8 on modern versions of macOS, Linux and Windows. You may encounter problems with graphical rendering if you use WSL. Your [contribution is welcome](https://flatland.aicrowd.com/misc/contributing.html) if you can help with this!  
 
 🏆 Challenges
 ---
 
 This library was developed specifically for the AIcrowd [Flatland challenges](http://flatland.aicrowd.com/research/top-challenge-solutions.html) in which we strongly encourage you to take part in!
 
+- [Flatland 3 Challenge](https://www.aicrowd.com/challenges/flatland-3) - ONGOING!
+- [AMLD 2021 Challenge](https://www.aicrowd.com/challenges/flatland)
 - [NeurIPS 2020 Challenge](https://www.aicrowd.com/challenges/neurips-2020-flatland-challenge/)
 - [2019 Challenge](https://www.aicrowd.com/challenges/flatland-challenge)
 
@@ -30,7 +32,7 @@ This library was developed specifically for the AIcrowd [Flatland challenges](ht
 Install [Anaconda](https://www.anaconda.com/distribution/) and create a new conda environment:
 
 ```console
-$ conda create python=3.6 --name flatland-rl
+$ conda create python=3.7 --name flatland-rl
 $ conda activate flatland-rl
 ```
 
@@ -57,7 +59,7 @@ $ git clone git@gitlab.aicrowd.com:flatland/flatland.git
 Once you have a copy of the source, install it with:
 
 ```console
-$ python setup.py install
+$ pip install -e .
 ```
 
 ### Test installation
@@ -77,7 +79,7 @@ python setup.py test
 👥 Credits
 ---
 
-This library was developed by [SBB](https://www.sbb.ch/en/), [Deutsche Bahn](https://www.deutschebahn.com/), [AIcrowd](https://www.aicrowd.com/) and [numerous contributors](http://flatland.aicrowd.com/misc/credits.html) and AIcrowd research fellows from the AIcrowd community. 
+This library was developed by [SBB](https://www.sbb.ch/en/), [Deutsche Bahn](https://www.deutschebahn.com/), [SNCF](https://www.sncf.com/en), [AIcrowd](https://www.aicrowd.com/) and [numerous contributors](http://flatland.aicrowd.com/misc/credits.html) and AIcrowd research fellows from the AIcrowd community.
 
 ➕ Contributions
 ---
@@ -93,6 +95,7 @@ Please follow the [Contribution Guidelines](https://flatland.aicrowd.com/misc/co
 🔗 Partners
 ---
 
-<a href="https://sbb.ch" target="_blank" style="margin-right:25px"><img src="https://i.imgur.com/OSCXtde.png" alt="SBB" width="200"/></a> 
-<a href="https://www.deutschebahn.com/" target="_blank" style="margin-right:25px"><img src="https://i.imgur.com/pjTki15.png" alt="DB"  width="200"/></a>
-<a href="https://www.aicrowd.com" target="_blank"><img src="https://avatars1.githubusercontent.com/u/44522764?s=200&v=4" alt="AICROWD"  width="200"/></a>
+<a href="https://sbb.ch" target="_blank" style="margin-right:30px"><img src="https://annpr2020.ch/wp-content/uploads/2020/06/SBB.png" alt="SBB" width="140"/></a> 
+<a href="https://www.deutschebahn.com/" target="_blank" style="margin-right:30px"><img src="https://i.imgur.com/pjTki15.png" alt="DB"  width="140"/></a>
+<a href="https://www.sncf.com/en" target="_blank" style="margin-right:30px"><img src="https://iconape.com/wp-content/png_logo_vector/logo-sncf.png" alt="SNCF"  width="140"/></a>
+<a href="https://www.aicrowd.com" target="_blank"><img src="https://i.imgur.com/kBZQGI9.png" alt="AIcrowd"  width="140"/></a>

flatland/__init__.py

@@ -4,4 +4,4 @@
 
 __author__ = """S.P. Mohanty"""
 __email__ = 'mohanty@aicrowd.com'
-__version__ = '2.2.2'
+__version__ = '3.0.0rc1'

flatland/cli.py

@@ -9,8 +9,8 @@ import numpy as np
 import redis
 
 from flatland.envs.rail_env import RailEnv
-from flatland.envs.rail_generators import complex_rail_generator
-from flatland.envs.line_generators import complex_line_generator
+from flatland.envs.rail_generators import sparse_rail_generator
+from flatland.envs.line_generators import sparse_line_generator
 from flatland.evaluators.service import FlatlandRemoteEvaluationService
 from flatland.utils.rendertools import RenderTool
 
@@ -18,35 +18,42 @@ from flatland.utils.rendertools import RenderTool
 @click.command()
 def demo(args=None):
     """Demo script to check installation"""
-    env = RailEnv(width=15, height=15, rail_generator=complex_rail_generator(
-        nr_start_goal=10,
-        nr_extra=1,
-        min_dist=8,
-        max_dist=99999), line_generator=complex_line_generator(), number_of_agents=5)
+    env = RailEnv(
+        width=30, 
+        height=30, 
+        rail_generator=sparse_rail_generator(
+            max_num_cities=3,
+            grid_mode=False,
+            max_rails_between_cities=4,
+            max_rail_pairs_in_city=2,
+            seed=0
+        ),
+        line_generator=sparse_line_generator(), 
+        number_of_agents=5)
 
     env._max_episode_steps = int(15 * (env.width + env.height))
     env_renderer = RenderTool(env)
 
-    while True:
-        obs, info = env.reset()
-        _done = False
-        # Run a single episode here
-        step = 0
-        while not _done:
-            # Compute Action
-            _action = {}
-            for _idx, _ in enumerate(env.agents):
-                _action[_idx] = np.random.randint(0, 5)
-            obs, all_rewards, done, _ = env.step(_action)
-            _done = done['__all__']
-            step += 1
-            env_renderer.render_env(
-                show=True,
-                frames=False,
-                show_observations=False,
-                show_predictions=False
-            )
-            time.sleep(0.3)
+    obs, info = env.reset()
+    _done = False
+    # Run a single episode here
+    step = 0
+    while not _done:
+        # Compute Action
+        _action = {}
+        for _idx, _ in enumerate(env.agents):
+            _action[_idx] = np.random.randint(0, 5)
+        obs, all_rewards, done, _ = env.step(_action)
+        _done = done['__all__']
+        step += 1
+        env_renderer.render_env(
+            show=True,
+            frames=False,
+            show_observations=False,
+            show_predictions=False
+        )
+        time.sleep(0.1)
+        
     return 0
 
 

flatland/envs/persistence.py

@@ -310,4 +310,4 @@ class RailEnvPersister(object):
         self.height, self.width = self.rail.grid.shape
         self.rail.height = self.height
         self.rail.width = self.width
-        self.dones = dict.fromkeys(list(range(self.get_num_agents())) + ["__all__"], False)
\ No newline at end of file
+        self.dones = dict.fromkeys(list(range(self.get_num_agents())) + ["__all__"], False)

flatland/envs/rail_env.py

@@ -15,7 +15,7 @@ from flatland.core.grid.grid4 import Grid4TransitionsEnum, Grid4Transitions
 from flatland.core.grid.grid4_utils import get_new_position
 from flatland.core.grid.grid_utils import IntVector2D
 from flatland.core.transition_map import GridTransitionMap
-from flatland.envs.agent_utils import EnvAgent, RailAgentStatus
+from flatland.envs.agent_utils import Agent, EnvAgent, RailAgentStatus
 from flatland.envs.distance_map import DistanceMap
 from flatland.envs.rail_env_action import RailEnvActions
 
@@ -477,6 +477,34 @@ class RailEnv(Environment):
 
         return
 
+    def _handle_end_reward(self, agent: EnvAgent) -> int:
+        '''
+        Handles end-of-episode reward for a particular agent.
+
+        Parameters
+        ----------
+        agent : EnvAgent
+        '''
+        reward = None
+        # agent done? (arrival_time is not None)
+        if agent.status == RailAgentStatus.DONE or agent.status == RailAgentStatus.DONE_REMOVED:
+            # if agent arrived earlier or on time = 0
+            # if agent arrived later = -ve reward based on how late
+            reward = min(agent.latest_arrival - agent.arrival_time, 0)
+
+        # Agents not done (arrival_time is None)
+        else:
+            # CANCELLED check (never departed)
+            if (agent.status == RailAgentStatus.READY_TO_DEPART):
+                reward = -1 * self.cancellation_factor * \
+                    (agent.get_travel_time_on_shortest_path(self.distance_map) + self.cancellation_time_buffer)
+
+            # Departed but never reached
+            if (agent.status == RailAgentStatus.ACTIVE):
+                reward = agent.get_current_delay(self._elapsed_steps, self.distance_map)
+        
+        return reward
+
     def step(self, action_dict_: Dict[int, RailEnvActions]):
         """
         Updates rewards for the agents at a step.
@@ -565,27 +593,8 @@ class RailEnv(Environment):
             
             for i_agent, agent in enumerate(self.agents):
                 
-                # agent done? (arrival_time is not None)
-                if agent.status == RailAgentStatus.DONE or agent.status == RailAgentStatus.DONE_REMOVED:
-                    
-                    # if agent arrived earlier or on time = 0
-                    # if agent arrived later = -ve reward based on how late
-                    reward = min(agent.latest_arrival - agent.arrival_time, 0)
-                    self.rewards_dict[i_agent] += reward
-                
-                # Agents not done (arrival_time is None)
-                else:
-                    
-                    # CANCELLED check (never departed)
-                    if (agent.status == RailAgentStatus.READY_TO_DEPART):
-                        reward = -1 * self.cancellation_factor * \
-                            (agent.get_travel_time_on_shortest_path(self.distance_map) + 0) # 0 replaced with buffer
-                        self.rewards_dict[i_agent] += reward
-
-                    # Departed but never reached
-                    if (agent.status == RailAgentStatus.ACTIVE):
-                        reward = agent.get_current_delay(self._elapsed_steps, self.distance_map)
-                        self.rewards_dict[i_agent] += reward
+                reward = self._handle_end_reward(agent)
+                self.rewards_dict[i_agent] += reward
                 
                 self.dones[i_agent] = True
 

flatland/envs/rail_generators.py

@@ -162,7 +162,7 @@ def sparse_rail_generator(*args, **kwargs):
 
 class SparseRailGen(RailGen):
 
-    def __init__(self, max_num_cities: int = 5, grid_mode: bool = False, max_rails_between_cities: int = 4,
+    def __init__(self, max_num_cities: int = 2, grid_mode: bool = False, max_rails_between_cities: int = 2,
                           max_rail_pairs_in_city: int = 2, seed=0) -> RailGenerator:
         """
         Generates railway networks with cities and inner city rails

setup.cfg

 [bumpversion]
-current_version = 2.2.2
+current_version = 3.0.0rc1
 commit = True
 tag = True
 

setup.py

@@ -80,6 +80,6 @@ setup(
     test_suite='tests',
     tests_require=test_requirements,
     url='https://gitlab.aicrowd.com/flatland/flatland',
-    version='3.0.0',
+    version='3.0.0rc1',
     zip_safe=False,
 )