{ "beta_end": 0.02, "beta_schedule": "squaredcos_cap_v2", "beta_start": 0.0001, "clip_sample": true, "clip_sample_range": 1.0, "crop_is_random": true, "crop_shape": [ 84, 84 ], "diffusion_step_embed_dim": 128, "do_mask_loss_for_padding": false, "down_dims": [ 512, 1024, 2048 ], "horizon": 16, "input_normalization_modes": { "observation.environment_state": "min_max", "observation.state": "min_max" }, "input_shapes": { "observation.environment_state": [ 16 ], "observation.state": [ 2 ] }, "kernel_size": 5, "n_action_steps": 8, "n_groups": 8, "n_obs_steps": 2, "noise_scheduler_type": "DDIM", "num_inference_steps": 10, "num_train_timesteps": 100, "output_normalization_modes": { "action": "min_max" }, "output_shapes": { "action": [ 2 ] }, "prediction_type": "epsilon", "pretrained_backbone_weights": null, "spatial_softmax_num_keypoints": 32, "use_film_scale_modulation": true, "use_group_norm": true, "vision_backbone": "resnet18" }