diff --git a/torch_training/railway/complex_scene.pkl b/torch_training/railway/complex_scene.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3225c39cd4675572ffca75776b37736ec4de7f31 Binary files /dev/null and b/torch_training/railway/complex_scene.pkl differ diff --git a/torch_training/railway/example_flatland_000.pkl b/torch_training/railway/example_flatland_000.pkl new file mode 100644 index 0000000000000000000000000000000000000000..64de2138400ee32332402e25f9eac810b5c8bfad Binary files /dev/null and b/torch_training/railway/example_flatland_000.pkl differ diff --git a/torch_training/railway/example_flatland_001.pkl b/torch_training/railway/example_flatland_001.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dcf8b8f51e3ce16c408c8d774bbbc7d29d6c242d Binary files /dev/null and b/torch_training/railway/example_flatland_001.pkl differ diff --git a/torch_training/railway/example_network_000.pkl b/torch_training/railway/example_network_000.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e102e21735416747cb8bd9f231ce6e20fdf514c0 Binary files /dev/null and b/torch_training/railway/example_network_000.pkl differ diff --git a/torch_training/railway/example_network_001.pkl b/torch_training/railway/example_network_001.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a9c5cc97c9c4bf4159db2134756f17fa0c4fce87 Binary files /dev/null and b/torch_training/railway/example_network_001.pkl differ diff --git a/torch_training/railway/example_network_002.pkl b/torch_training/railway/example_network_002.pkl new file mode 100644 index 0000000000000000000000000000000000000000..37647ac2871801d2d08fd65276889e2b232c1170 Binary files /dev/null and b/torch_training/railway/example_network_002.pkl differ diff --git a/torch_training/railway/example_network_003.pkl b/torch_training/railway/example_network_003.pkl new file mode 100644 index 0000000000000000000000000000000000000000..658db6388315948bb1cfeb7dca6891f24cd4961f Binary files /dev/null and b/torch_training/railway/example_network_003.pkl differ diff --git a/torch_training/training_navigation.py b/torch_training/training_navigation.py index c473e5284bcb538dd9f59748e54b5a1d6946be42..2a4af22ad148814f397dd32b7e96f3f6d666c70f 100644 --- a/torch_training/training_navigation.py +++ b/torch_training/training_navigation.py @@ -32,21 +32,20 @@ env = RailEnv(width=20, height=20, rail_generator=random_rail_generator(cell_type_relative_proportion=transition_probability), number_of_agents=1) -""" + env = RailEnv(width=15, height=15, rail_generator=complex_rail_generator(nr_start_goal=10, nr_extra=10, min_dist=10, max_dist=99999, seed=0), number_of_agents=1) """ -env = RailEnv(width=20, - height=20, - rail_generator=rail_from_list_of_saved_GridTransitionMap_generator( - ['../notebooks/temp.npy']), - number_of_agents=3) -""" -env_renderer = RenderTool(env, gl="QT") +env = RailEnv(width=10, + height=20) +env.load("./railway/complex_scene.pkl") +env.reset(False, False) + +env_renderer = RenderTool(env, gl="PILSVG") handle = env.get_agent_handles() state_size = 105 * 2 @@ -120,7 +119,7 @@ def norm_obs_clip(obs, clip_min=-1, clip_max=1): for trials in range(1, n_trials + 1): # Reset environment - obs = env.reset() + obs = env.reset(False,False) final_obs = obs.copy() final_obs_next = obs.copy() @@ -141,9 +140,9 @@ for trials in range(1, n_trials + 1): score = 0 env_done = 0 # Run episode - for step in range(100): + for step in range(360): if demo: - env_renderer.renderEnv(show=True) + env_renderer.renderEnv(show=True,show_observations=False) # print(step) # Action for a in range(env.get_num_agents()):