diff --git a/examples/training_navigation.py b/examples/training_navigation.py index 60dc1adbf473382aad4ed0dde3ab9a13e64e7785..975d33fb3139ebc2040b941dbe73d8aeb3b225eb 100644 --- a/examples/training_navigation.py +++ b/examples/training_navigation.py @@ -54,7 +54,8 @@ for trials in range(1, n_trials + 1): # Run episode for step in range(100): - #env_renderer.renderEnv(show=True) + if trials >= 114: + env_renderer.renderEnv(show=True) # Action for a in range(env.number_of_agents): diff --git a/flatland/envs/rail_env.py b/flatland/envs/rail_env.py index 22c072a838085d40f045a496b1aa6cc8aa778fc3..36040d5cf66f1adc74faaade7e45acbd711676e0 100644 --- a/flatland/envs/rail_env.py +++ b/flatland/envs/rail_env.py @@ -547,7 +547,7 @@ class RailEnv(Environment): global_reward = 1 * beta # Reset the step rewards - self.rewards_dict = {} + self.rewards_dict = dict() for handle in self.agents_handles: self.rewards_dict[handle] = 0