From 1ada946674c049d615887085d9a750bf5ac12a72 Mon Sep 17 00:00:00 2001 From: Kaeun Kim Date: Tue, 21 Oct 2025 14:45:11 +0100 Subject: [PATCH 1/2] fix: training loop example for sumo rl --- src/envs/sumo_rl_env/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/envs/sumo_rl_env/README.md b/src/envs/sumo_rl_env/README.md index e35035ae..1cb045f6 100644 --- a/src/envs/sumo_rl_env/README.md +++ b/src/envs/sumo_rl_env/README.md @@ -220,7 +220,7 @@ for episode in range(10): action_id = np.random.choice(result.observation.action_mask) # Take action - result = env.step(SumoAction(phase_id=action_id)) + result = env.step(SumoAction(phase_id=int(action_id))) episode_reward += result.reward or 0 steps += 1 From 9c90de5e72dfa0bcac94e0fabe88dd16bed2f2ab Mon Sep 17 00:00:00 2001 From: Kaeun Kim Date: Tue, 21 Oct 2025 14:53:15 +0100 Subject: [PATCH 2/2] fix: sumo rl simple example --- examples/sumo_rl_simple.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/sumo_rl_simple.py b/examples/sumo_rl_simple.py index ec5f08ae..8b02c694 100644 --- a/examples/sumo_rl_simple.py +++ b/examples/sumo_rl_simple.py @@ -56,7 +56,7 @@ def main(): action_id = np.random.choice(result.observation.action_mask) # Take action - result = env.step(SumoAction(phase_id=action_id)) + result = env.step(SumoAction(phase_id=int(action_id))) episode_reward += result.reward or 0 steps += 1