{ "algo_name": "cql", "experiment": { "name": "test", "validate": false, "logging": { "terminal_output_to_txt": true, "log_tb": true, "log_wandb": false, "wandb_proj_name": "debug" }, "save": { "enabled": true, "every_n_seconds": null, "every_n_epochs": 50, "epochs": [], "on_best_validation": false, "on_best_rollout_return": false, "on_best_rollout_success_rate": true }, "epoch_every_n_steps": 100, "validation_epoch_every_n_steps": 10, "env": null, "additional_envs": null, "render": false, "render_video": true, "keep_all_videos": false, "video_skip": 5, "rollout": { "enabled": true, "n": 50, "horizon": 400, "rate": 50, "warmstart": 0, "terminate_on_success": true } }, "train": { "data": null, "output_dir": "../cql_trained_models", "num_data_workers": 0, "hdf5_cache_mode": "all", "hdf5_use_swmr": true, "hdf5_load_next_obs": true, "hdf5_normalize_obs": false, "hdf5_filter_key": null, "hdf5_validation_filter_key": null, "seq_length": 1, "pad_seq_length": true, "frame_stack": 1, "pad_frame_stack": true, "dataset_keys": [ "actions", "rewards", "dones" ], "goal_mode": null, "cuda": true, "batch_size": 1024, "num_epochs": 2000, "seed": 1 }, "algo": { "optim_params": { "critic": { "learning_rate": { "initial": 0.001, "decay_factor": 0.0, "epoch_schedule": [] }, "regularization": { "L2": 0.0 } }, "actor": { "learning_rate": { "initial": 0.0003, "decay_factor": 0.0, "epoch_schedule": [] }, "regularization": { "L2": 0.0 } } }, "discount": 0.99, "n_step": 1, "target_tau": 0.005, "actor": { "bc_start_steps": 0, "target_entropy": "default", "max_gradient_norm": null, "net": { "type": "gaussian", "common": { "std_activation": "exp", "use_tanh": true, "low_noise_eval": true }, "gaussian": { "init_last_fc_weight": 0.001, "init_std": 0.3, "fixed_std": false } }, "layer_dims": [ 300, 400 ] }, "critic": { "use_huber": false, "max_gradient_norm": null, "value_bounds": null, "num_action_samples": 1, "cql_weight": 1.0, "deterministic_backup": true, "min_q_weight": 1.0, "target_q_gap": 5.0, "num_random_actions": 10, "ensemble": { "n": 2 }, "layer_dims": [ 300, 400 ] } }, "observation": { "modalities": { "obs": { "low_dim": [ "robot0_eef_pos", "robot0_eef_quat", "robot0_gripper_qpos", "object" ], "rgb": [], "depth": [], "scan": [] }, "goal": { "low_dim": [], "rgb": [], "depth": [], "scan": [] } }, "encoder": { "low_dim": { "core_class": null, "core_kwargs": {}, "obs_randomizer_class": null, "obs_randomizer_kwargs": {} }, "rgb": { "core_class": "VisualCore", "core_kwargs": {}, "obs_randomizer_class": null, "obs_randomizer_kwargs": {} }, "depth": { "core_class": "VisualCore", "core_kwargs": {}, "obs_randomizer_class": null, "obs_randomizer_kwargs": {} }, "scan": { "core_class": "ScanCore", "core_kwargs": {}, "obs_randomizer_class": null, "obs_randomizer_kwargs": {} } } }, "meta": { "hp_base_config_file": null, "hp_keys": [], "hp_values": [] } }