--- tags: - Hover - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: ppo results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Hover type: Hover metrics: - type: mean_reward value: 0.00 +/- 0.00 name: mean_reward verified: false --- # (MarineGym) **ppo** Agent Playing **Hover** This is a trained model of a ppo agent playing Hover. # Hyperparameters ```python {'_content': {'algo': {'name': 'ppo', 'train_every': 32, 'ppo_epochs': 4, 'num_minibatches': 16, 'priv_actor': False, 'priv_critic': False, 'checkpoint_path': None}, 'enable_livestream': False, 'env': {'num_envs': 2048, 'env_spacing': 6, 'max_episode_length': 200}, 'eval_interval': -1, 'headless': True, 'hf_entity': 'marinegym', 'max_iters': -1, 'save_interval': -1, 'seed': 0, 'sim': {'dt': 0.016, 'substeps': 1, 'gravity': [0, 0, -9.81], 'replicate_physics': False, 'use_flatcache': True, 'use_gpu_pipeline': True, 'device': 'cuda:0', 'solver_type': 1, 'use_gpu': True, 'bounce_threshold_velocity': 0.2, 'friction_offset_threshold': 0.04, 'friction_correlation_distance': 0.025, 'enable_stabilization': True, 'gpu_max_rigid_contact_count': 524288, 'gpu_max_rigid_patch_count': 163840, 'gpu_found_lost_pairs_capacity': 4194304, 'gpu_found_lost_aggregate_pairs_capacity': 33554432, 'gpu_total_aggregate_pairs_capacity': 4194304, 'gpu_max_soft_body_contacts': 1048576, 'gpu_max_particle_contacts': 1048576, 'gpu_heap_capacity': 67108864, 'gpu_temp_buffer_capacity': 16777216, 'gpu_max_num_partitions': 8, 'enable_scene_query_support': True}, 'task': {'env': {'num_envs': 2048, 'env_spacing': 6, 'max_episode_length': 200}, 'sim': {'dt': 0.016, 'substeps': 1, 'gravity': [0, 0, -9.81], 'replicate_physics': False, 'use_flatcache': True, 'use_gpu_pipeline': True, 'device': 'cuda:0', 'solver_type': 1, 'use_gpu': True, 'bounce_threshold_velocity': 0.2, 'friction_offset_threshold': 0.04, 'friction_correlation_distance': 0.025, 'enable_stabilization': True, 'gpu_max_rigid_contact_count': 524288, 'gpu_max_rigid_patch_count': 163840, 'gpu_found_lost_pairs_capacity': 4194304, 'gpu_found_lost_aggregate_pairs_capacity': 33554432, 'gpu_total_aggregate_pairs_capacity': 4194304, 'gpu_max_soft_body_contacts': 1048576, 'gpu_max_particle_contacts': 1048576, 'gpu_heap_capacity': 67108864, 'gpu_temp_buffer_capacity': 16777216, 'gpu_max_num_partitions': 8}, 'name': 'Hover', 'drone_model': {'name': 'BlueROVHeavy', 'controller': 'LeePositionController'}, 'force_sensor': False, 'time_encoding': True, 'reward_effort_weight': 0.1, 'reward_action_smoothness_weight': 0.0, 'reward_motion_smoothness_weight': 0.0, 'reward_distance_scale': 1.2, 'action_transform': None, 'has_flow': True, 'max_flow_velocity': [1.0, 1.0, 1.0, 0.0, 0.0, 0.0], 'flow_velocity_gaussian_noise': [0.2, 0.2, 0.2, 0.0, 0.0, 0.0]}, 'total_frames': 50000, 'upload_model': True, 'viewer': {'resolution': [960, 720], 'eye': [8, 0.0, 6.0], 'lookat': [0.0, 0.0, 1.0]}, 'wandb': {'group': 'Hover', 'run_name': 'Hover-ppo', 'job_type': 'train', 'entity': 'zebin', 'project': 'omnidrones', 'mode': 'online', 'run_id': None, 'monitor_gym': True, 'tags': None}}, '_flags_cache': {'allow_objects': None, 'convert': None, 'readonly': None, 'struct': False}, '_metadata': ContainerMetadata(ref_type=typing.Any, object_type=, optional=True, key=None, flags={'struct': False}, flags_root=False, resolver_cache=defaultdict(, {'now': {('%H-%M-%S',): '10-05-34', ('%Y-%m-%d',): '2025-02-22'}}), key_type=typing.Any, element_type=typing.Any), '_parent': None} ```