last training set up before freeze

RLLib_training/experiment_configs/config_example/config.gin

+run_experiment.name = "experiment_example"
+run_experiment.num_iterations = 1002
+run_experiment.save_every = 100
+run_experiment.hidden_sizes = [32, 32]
+
+run_experiment.map_width = 20
+run_experiment.map_height = 20
+run_experiment.n_agents = 7#{"grid_search": [3, 4, 5, 6, 7, 8]}
+run_experiment.rail_generator = "complex_rail_generator"
+run_experiment.nr_extra = 5
+run_experiment.policy_folder_name = "ppo_policy_two_obs_with_predictions_n_agents_{config[n_agents]}_"#_map_size_{config[map_width]}"
+
+run_experiment.seed = 123
+
+run_experiment.conv_model = False
+
+run_experiment.obs_builder = @TreeObsForRailEnv()
+TreeObsForRailEnv.predictor = @ShortestPathPredictorForRailEnv()
+TreeObsForRailEnv.max_depth = 2
+
+run_experiment.entropy_coeff = 0.001
+run_experiment.kl_coeff = 0.2 
+run_experiment.lambda_gae = 0.9
+run_experiment.step_memory = 2
+run_experiment.min_dist = 10