Why my hyper_opt algorithm returns a bad 'best configuration' with same parameters written several times

I recently worked on a hyperparameters optimization with a search algorithm.

The purpose is to train an agent in an OpenAI Gym environment.

The problem is the following one : when I realize a hyperparameters optimization with a hyperOpt algorithm from ray.tune, it returns me a best config with same parameters several times in this configuration. Furthermore, I cannot use this best configuration to run a unit training. I deduced there was a problem.

I show you below my code below :

config = {
             "env": "LunarLander-v2",
             "sgd_minibatch_size": 1000,
             "num_sgd_iter": 1000,
             "lr": tune.uniform(5e-6, 5e-2),
             "lambda": tune.uniform(0.6, 0.9),
             "vf_loss_coeff": 0.7,
             "kl_target": 0.01,
             "kl_coeff": tune.uniform(0.5, 0.9),
             "entropy_coeff": 0.001,
             "clip_param": tune.uniform(0.4, 0.99),
             "train_batch_size": 25000, # taille de l'épisode
             # "monitor": True,
             # "model": {"free_log_std": True},
             "num_workers": 4,
             "num_gpus": 0,
             # "rollout_fragment_length":3
             # "batch_mode": "complete_episodes"
         }


config = explore(config)
optimizer = HyperOptSearch(metric="episode_reward_mean", mode="max", n_initial_points=1, random_state_seed=7, space=config)

# optimizer = ConcurrencyLimiter(optimizer, max_concurrent=4)

tuner = tune.Tuner(
    "PPO",
    tune_config=tune.TuneConfig(
        metric="episode_reward_mean",  # the metric we want to study
        mode="max",  # maximize the metric
        search_alg=optimizer,
        # num_samples will repeat the entire config 'num_samples' times == Number of trials dans l'output 'Status'
        num_samples=1,
    ),
    run_config=air.RunConfig(stop={"training_iteration": 1}),
    # limite le nombre d'épisode pour chaque croisement d'hyperparamètres

)
results = tuner.fit()

best_conf=results.get_best_result().config

print(f"\n ##############################################\n Meilleure configuration : {best_conf}\n ##############################################\n")

So here is the best config of this tuning (it is long so also difficult to see, but all parameters are written several times) :

***Best configuration*** : {'extra_python_environs_for_driver': {}, 'extra_python_environs_for_worker': {}, 'num_gpus': 0, 'num_cpus_per_worker': 1, 'num_gpus_per_worker': 0, '_fake_gpus': False, 'custom_resources_per_worker': {}, 'placement_strategy': 'PACK', 'eager_tracing': False, 'eager_max_retraces': 20, 'tf_session_args': {'intra_op_parallelism_threads': 2, 'inter_op_parallelism_threads': 2, 'gpu_options': {'allow_growth': True}, 'log_device_placement': False, 'device_count': {'CPU': 1}, 'allow_soft_placement': True}, 'local_tf_session_args': {'intra_op_parallelism_threads': 8, 'inter_op_parallelism_threads': 8}, 'env': 'LunarLander-v2', 'env_config': {}, 'observation_space': None, 'action_space': None, 'env_task_fn': None, 'render_env': False, 'clip_rewards': None, 'normalize_actions': True, 'clip_actions': False, 'disable_env_checking': False, 'num_workers': 4, 'num_envs_per_worker': 1, 'sample_collector': <class 'ray.rllib.evaluation.collectors.simple_list_collector.SimpleListCollector'>, 'sample_async': False, 'enable_connectors': False, 'rollout_fragment_length': 6250, 'batch_mode': 'truncate_episodes', 'remote_worker_envs': False, 'remote_env_batch_wait_ms': 0, 'validate_workers_after_construction': True, 'ignore_worker_failures': False, 'recreate_failed_workers': False, 'restart_failed_sub_environments': False, 'num_consecutive_worker_failures_tolerance': 100, 'horizon': None, 'soft_horizon': False, 'no_done_at_end': False, 'preprocessor_pref': 'deepmind', 'observation_filter': 'NoFilter', 'synchronize_filters': True, 'compress_observations': False, 'enable_tf1_exec_eagerly': False, 'sampler_perf_stats_ema_coef': None, 'gamma': 0.99, 'lr': 0.03346975115973727, 'train_batch_size': 25000, 'model': {'_use_default_native_models': False, '_disable_preprocessor_api': False, '_disable_action_flattening': False, 'fcnet_hiddens': [256, 256], 'fcnet_activation': 'tanh', 'conv_filters': None, 'conv_activation': 'relu', 'post_fcnet_hiddens': [], 'post_fcnet_activation': 'relu', 'free_log_std': False, 'no_final_linear': False, 'vf_share_layers': False, 'use_lstm': False, 'max_seq_len': 20, 'lstm_cell_size': 256, 'lstm_use_prev_action': False, 'lstm_use_prev_reward': False, '_time_major': False, 'use_attention': False, 'attention_num_transformer_units': 1, 'attention_dim': 64, 'attention_num_heads': 1, 'attention_head_dim': 32, 'attention_memory_inference': 50, 'attention_memory_training': 50, 'attention_position_wise_mlp_dim': 32, 'attention_init_gru_gate_bias': 2.0, 'attention_use_n_prev_actions': 0, 'attention_use_n_prev_rewards': 0, 'framestack': True, 'dim': 84, 'grayscale': False, 'zero_mean': True, 'custom_model': None, 'custom_model_config': {}, 'custom_action_dist': None, 'custom_preprocessor': None, 'lstm_use_prev_action_reward': -1}, 'optimizer': {}, 'explore': True, 'exploration_config': {'type': 'StochasticSampling'}, 'input_config': {}, 'actions_in_input_normalized': False, 'postprocess_inputs': False, 'shuffle_buffer_size': 0, 'output': None, 'output_config': {}, 'output_compress_columns': ['obs', 'new_obs'], 'output_max_file_size': 67108864, 'evaluation_interval': None, 'evaluation_duration': 10, 'evaluation_duration_unit': 'episodes', 'evaluation_sample_timeout_s': 180.0, 'evaluation_parallel_to_training': False, 'evaluation_config': {'extra_python_environs_for_driver': {}, 'extra_python_environs_for_worker': {}, 'num_gpus': 0, 'num_cpus_per_worker': 1, 'num_gpus_per_worker': 0, '_fake_gpus': False, 'custom_resources_per_worker': {}, 'placement_strategy': 'PACK', 'eager_tracing': False, 'eager_max_retraces': 20, 'tf_session_args': {'intra_op_parallelism_threads': 2, 'inter_op_parallelism_threads': 2, 'gpu_options': {'allow_growth': True}, 'log_device_placement': False, 'device_count': {'CPU': 1}, 'allow_soft_placement': True}, 'local_tf_session_args': {'intra_op_parallelism_threads': 8, 'inter_op_parallelism_threads': 8}, 'env': 'LunarLander-v2', 'env_config': {}, 'observation_space': None, 'action_space': None, 'env_task_fn': None, 'render_env': False, 'clip_rewards': None, 'normalize_actions': True, 'clip_actions': False, 'disable_env_checking': False, 'num_workers': 4, 'num_envs_per_worker': 1, 'sample_collector': <class 'ray.rllib.evaluation.collectors.simple_list_collector.SimpleListCollector'>, 'sample_async': False, 'enable_connectors': False, 'rollout_fragment_length': 6250, 'batch_mode': 'truncate_episodes', 'remote_worker_envs': False, 'remote_env_batch_wait_ms': 0, 'validate_workers_after_construction': True, 'ignore_worker_failures': False, 'recreate_failed_workers': False, 'restart_failed_sub_environments': False, 'num_consecutive_worker_failures_tolerance': 100, 'horizon': None, 'soft_horizon': False, 'no_done_at_end': False, 'preprocessor_pref': 'deepmind', 'observation_filter': 'NoFilter', 'synchronize_filters': True, 'compress_observations': False, 'enable_tf1_exec_eagerly': False, 'sampler_perf_stats_ema_coef': None, 'gamma': 0.99, 'lr': 0.03346975115973727, 'train_batch_size': 25000, 'model': {'_use_default_native_models': False, '_disable_preprocessor_api': False, '_disable_action_flattening': False, 'fcnet_hiddens': [256, 256], 'fcnet_activation': 'tanh', 'conv_filters': None, 'conv_activation': 'relu', 'post_fcnet_hiddens': [], 'post_fcnet_activation': 'relu', 'free_log_std': False, 'no_final_linear': False, 'vf_share_layers': False, 'use_lstm': False, 'max_seq_len': 20, 'lstm_cell_size': 256, 'lstm_use_prev_action': False, 'lstm_use_prev_reward': False, '_time_major': False, 'use_attention': False, 'attention_num_transformer_units': 1, 'attention_dim': 64, 'attention_num_heads': 1, 'attention_head_dim': 32, 'attention_memory_inference': 50, 'attention_memory_training': 50, 'attention_position_wise_mlp_dim': 32, 'attention_init_gru_gate_bias': 2.0, 'attention_use_n_prev_actions': 0, 'attention_use_n_prev_rewards': 0, 'framestack': True, 'dim': 84, 'grayscale': False, 'zero_mean': True, 'custom_model': None, 'custom_model_config': {}, 'custom_action_dist': None, 'custom_preprocessor': None, 'lstm_use_prev_action_reward': -1}, 'optimizer': {}, 'explore': True, 'exploration_config': {'type': 'StochasticSampling'}, 'input_config': {}, 'actions_in_input_normalized': False, 'postprocess_inputs': False, 'shuffle_buffer_size': 0, 'output': None, 'output_config': {}, 'output_compress_columns': ['obs', 'new_obs'], 'output_max_file_size': 67108864, 'evaluation_interval': None, 'evaluation_duration': 10, 'evaluation_duration_unit': 'episodes', 'evaluation_sample_timeout_s': 180.0, 'evaluation_parallel_to_training': False, 'evaluation_config': {}, 'off_policy_estimation_methods': {}, 'evaluation_num_workers': 0, 'always_attach_evaluation_results': False, 'in_evaluation': False, 'sync_filters_on_rollout_workers_timeout_s': 60.0, 'keep_per_episode_custom_metrics': False, 'metrics_episode_collection_timeout_s': 60.0, 'metrics_num_episodes_for_smoothing': 100, 'min_time_s_per_iteration': None, 'min_train_timesteps_per_iteration': 0, 'min_sample_timesteps_per_iteration': 0, 'logger_creator': None, 'logger_config': None, 'log_level': 'WARN', 'log_sys_usage': True, 'fake_sampler': False, 'seed': None, '_tf_policy_handles_more_than_one_loss': False, '_disable_preprocessor_api': False, '_disable_action_flattening': False, '_disable_execution_plan_api': True, 'simple_optimizer': False, 'monitor': -1, 'evaluation_num_episodes': -1, 'metrics_smoothing_episodes': -1, 'timesteps_per_iteration': -1, 'min_iter_time_s': -1, 'collect_metrics_timeout': -1, 'buffer_size': -1, 'prioritized_replay': -1, 'learning_starts': -1, 'replay_batch_size': -1, 'replay_sequence_length': None, 'prioritized_replay_alpha': -1, 'prioritized_replay_beta': -1, 'prioritized_replay_eps': -1, 'min_time_s_per_reporting': -1, 'min_train_timesteps_per_reporting': -1, 'min_sample_timesteps_per_reporting': -1, 'input_evaluation': -1, 'lr_schedule': None, 'use_critic': True, 'use_gae': True, 'kl_coeff': 0.5003002941138288, 'sgd_minibatch_size': 1000, 'num_sgd_iter': 1000, 'shuffle_sequences': True, 'vf_loss_coeff': 0.7, 'entropy_coeff': 0.001, 'entropy_coeff_schedule': None, 'clip_param': 0.9429343265857039, 'vf_clip_param': 10.0, 'grad_clip': None, 'kl_target': 0.01, 'vf_share_layers': -1, 'lambda': 0.7125712711928637, 'input': 'sampler', 'multiagent': {'policies': {'default_policy': <ray.rllib.policy.policy.PolicySpec object at 0x7f1d0c4073d0>}, 'policy_map_capacity': 100, 'policy_map_cache': None, 'policy_mapping_fn': None, 'policies_to_train': None, 'observation_fn': None, 'replay_mode': 'independent', 'count_steps_by': 'env_steps'}, 'callbacks': <class 'ray.rllib.algorithms.callbacks.DefaultCallbacks'>, 'create_env_on_driver': False, 'custom_eval_function': None, 'framework': 'tf', 'num_cpus_for_driver': 1}, 'off_policy_estimation_methods': {}, 'evaluation_num_workers': 0, 'always_attach_evaluation_results': False, 'in_evaluation': False, 'sync_filters_on_rollout_workers_timeout_s': 60.0, 'keep_per_episode_custom_metrics': False, 'metrics_episode_collection_timeout_s': 60.0, 'metrics_num_episodes_for_smoothing': 100, 'min_time_s_per_iteration': None, 'min_train_timesteps_per_iteration': 0, 'min_sample_timesteps_per_iteration': 0, 'logger_creator': None, 'logger_config': None, 'log_level': 'WARN', 'log_sys_usage': True, 'fake_sampler': False, 'seed': None, '_tf_policy_handles_more_than_one_loss': False, '_disable_preprocessor_api': False, '_disable_action_flattening': False, '_disable_execution_plan_api': True, 'simple_optimizer': False, 'monitor': -1, 'evaluation_num_episodes': -1, 'metrics_smoothing_episodes': -1, 'timesteps_per_iteration': -1, 'min_iter_time_s': -1, 'collect_metrics_timeout': -1, 'buffer_size': -1, 'prioritized_replay': -1, 'learning_starts': -1, 'replay_batch_size': -1, 'replay_sequence_length': None, 'prioritized_replay_alpha': -1, 'prioritized_replay_beta': -1, 'prioritized_replay_eps': -1, 'min_time_s_per_reporting': -1, 'min_train_timesteps_per_reporting': -1, 'min_sample_timesteps_per_reporting': -1, 'input_evaluation': -1, 'lr_schedule': None, 'use_critic': True, 'use_gae': True, 'kl_coeff': 0.5003002941138288, 'sgd_minibatch_size': 1000, 'num_sgd_iter': 1000, 'shuffle_sequences': True, 'vf_loss_coeff': 0.7, 'entropy_coeff': 0.001, 'entropy_coeff_schedule': None, 'clip_param': 0.9429343265857039, 'vf_clip_param': 10.0, 'grad_clip': None, 'kl_target': 0.01, 'vf_share_layers': -1, 'lambda': 0.7125712711928637, 'input': 'sampler', 'multiagent': {'policies': {'default_policy': <ray.rllib.policy.policy.PolicySpec object at 0x7f1d0c407580>}, 'policy_map_capacity': 100, 'policy_map_cache': None, 'policy_mapping_fn': None, 'policies_to_train': None, 'observation_fn': None, 'replay_mode': 'independent', 'count_steps_by': 'env_steps'}, 'callbacks': <class 'ray.rllib.algorithms.callbacks.DefaultCallbacks'>, 'create_env_on_driver': False, 'custom_eval_function': None, 'framework': 'tf', 'num_cpus_for_driver': 1}

I add that I found this on the ray documentation. How could I adapt it to my case ?

import os
logdir = results.get_best_result("mean_accuracy", mode="max").log_dir
state_dict = torch.load(os.path.join(logdir, "model.pth"))
model = ConvNet()
model.load_state_dict(state_dict)

Thank you by advance for your time

You're currently running with only num_samples=1, which should only produce a single result with one sampled configuration. RLlib is populating the best_conf with other default configs, but the configs that you specified are still there.

For resuming your RLlib experiment, this resource from the docs may be useful (restoring and continuing training an RLlib algorithm).