diff --git a/env-data/railway/example_network_000.pkl b/env-data/railway/example_network_000.pkl new file mode 100644 index 0000000000000000000000000000000000000000..280688c2629331621ab2ea80b4b096226464e653 Binary files /dev/null and b/env-data/railway/example_network_000.pkl differ diff --git a/env-data/railway/example_network_001.pkl b/env-data/railway/example_network_001.pkl new file mode 100644 index 0000000000000000000000000000000000000000..801f95149dec6eb4d47fd14e36d30f2541480188 Binary files /dev/null and b/env-data/railway/example_network_001.pkl differ diff --git a/env-data/railway/example_network_002.pkl b/env-data/railway/example_network_002.pkl new file mode 100644 index 0000000000000000000000000000000000000000..898d54ebeb823e48790d4661ffe75a6940cd0712 Binary files /dev/null and b/env-data/railway/example_network_002.pkl differ diff --git a/examples/training_navigation.py b/examples/training_navigation.py index 15b8ddde15b287418ae41229a7bf4edeed92772c..0cb9d275eda2a01932c4f632c1abd4fb662f4037 100644 --- a/examples/training_navigation.py +++ b/examples/training_navigation.py @@ -36,7 +36,7 @@ env = RailEnv(width=20, 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=10) + number_of_agents=5) """ env = RailEnv(width=20, @@ -46,7 +46,7 @@ env = RailEnv(width=20, number_of_agents=3) """ -env_renderer = RenderTool(env, gl="QT") +env_renderer = RenderTool(env, gl="QTSVG") handle = env.get_agent_handles() state_size = 105 * 2 @@ -66,7 +66,7 @@ action_prob = [0] * 4 agent_obs = [None] * env.get_num_agents() agent_next_obs = [None] * env.get_num_agents() agent = Agent(state_size, action_size, "FC", 0) -agent.qnetwork_local.load_state_dict(torch.load('../flatland/baselines/Nets/avoid_checkpoint15000.pth')) +agent.qnetwork_local.load_state_dict(torch.load('./flatland/baselines/Nets/avoid_checkpoint15000.pth')) demo = True @@ -144,7 +144,6 @@ for trials in range(1, n_trials + 1): for step in range(100): if demo: env_renderer.renderEnv(show=True) - time.sleep(0.1) # print(step) # Action for a in range(env.get_num_agents()):