Merge branch 'main' of https://github.com/LucasAlegre/sumo-rl

README.md

@@ -1,5 +1,6 @@
 <img src="docs/_static/logo.png" align="right" width="30%"/>
 
+[![DOI](https://zenodo.org/badge/161216111.svg)](https://zenodo.org/doi/10.5281/zenodo.10869789)
 [![tests](https://github.com/LucasAlegre/sumo-rl/actions/workflows/linux-test.yml/badge.svg)](https://github.com/LucasAlegre/sumo-rl/actions/workflows/linux-test.yml)
 [![PyPI version](https://badge.fury.io/py/sumo-rl.svg)](https://badge.fury.io/py/sumo-rl)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://pre-commit.com/)

sumo_rl/__init__.py

@@ -19,4 +19,4 @@
 )
 
 
-__version__ = "1.4.3"
+__version__ = "1.4.4"

sumo_rl/environment/env.py

@@ -305,7 +305,7 @@ def step(self, action: Union[dict, int]):
             If single_agent is True, action is an int, otherwise it expects a dict with keys corresponding to traffic signal ids.
         """
         # No action, follow fixed TL defined in self.phases
-        if action is None or action == {}:
+        if self.fixed_ts or action is None or action == {}:
             for _ in range(self.delta_time):
                 self._sumo_step()
         else:
@@ -364,15 +364,27 @@ def _compute_info(self):
 
     def _compute_observations(self):
         self.observations.update(
-            {ts: self.traffic_signals[ts].compute_observation() for ts in self.ts_ids if self.traffic_signals[ts].time_to_act}
+            {
+                ts: self.traffic_signals[ts].compute_observation()
+                for ts in self.ts_ids
+                if self.traffic_signals[ts].time_to_act or self.fixed_ts
+            }
         )
-        return {ts: self.observations[ts].copy() for ts in self.observations.keys() if self.traffic_signals[ts].time_to_act}
+        return {
+            ts: self.observations[ts].copy()
+            for ts in self.observations.keys()
+            if self.traffic_signals[ts].time_to_act or self.fixed_ts
+        }
 
     def _compute_rewards(self):
         self.rewards.update(
-            {ts: self.traffic_signals[ts].compute_reward() for ts in self.ts_ids if self.traffic_signals[ts].time_to_act}
+            {
+                ts: self.traffic_signals[ts].compute_reward()
+                for ts in self.ts_ids
+                if self.traffic_signals[ts].time_to_act or self.fixed_ts
+            }
         )
-        return {ts: self.rewards[ts] for ts in self.rewards.keys() if self.traffic_signals[ts].time_to_act}
+        return {ts: self.rewards[ts] for ts in self.rewards.keys() if self.traffic_signals[ts].time_to_act or self.fixed_ts}
 
     @property
     def observation_space(self):
@@ -580,10 +592,16 @@ def step(self, action):
                 "It is currently {}".format(agent, self.action_spaces[agent].n, action)
             )
 
-        self.env._apply_actions({agent: action})
+        if not self.env.fixed_ts:
+            self.env._apply_actions({agent: action})
 
         if self._agent_selector.is_last():
-            self.env._run_steps()
+            if not self.env.fixed_ts:
+                self.env._run_steps()
+            else:
+                for _ in range(self.env.delta_time):
+                    self.env._sumo_step()
+
             self.env._compute_observations()
             self.rewards = self.env._compute_rewards()
             self.compute_info()