config.gin

run_experiment.name = "observation_benchmark_results"
run_experiment.num_iterations = 1002
run_experiment.save_every = 50
run_experiment.hidden_sizes = [32, 32]

run_experiment.map_width = 20
run_experiment.map_height = 20
run_experiment.n_agents = 8
run_experiment.rail_generator = "complex_rail_generator"
run_experiment.nr_extra = {"grid_search": [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]}
run_experiment.policy_folder_name = "ppo_policy_nr_extra_{config[nr_extra]}_"

run_experiment.horizon = 50
run_experiment.seed = 123

#run_experiment.conv_model = {"grid_search": [True, False]}
run_experiment.conv_model = False

#run_experiment.obs_builder = {"grid_search": [@GlobalObsForRailEnv(), @GlobalObsForRailEnvDirectionDependent]}# [@TreeObsForRailEnv(), @GlobalObsForRailEnv() ]}
run_experiment.obs_builder = @TreeObsForRailEnv()
TreeObsForRailEnv.max_depth = 2
LocalObsForRailEnv.view_radius = 5

run_experiment.entropy_coeff = 0.01