| default_settings: null | |
| behaviors: | |
| Worm: | |
| trainer_type: ppo | |
| hyperparameters: | |
| batch_size: 2024 | |
| buffer_size: 20240 | |
| learning_rate: 0.0003 | |
| beta: 0.005 | |
| epsilon: 0.2 | |
| lambd: 0.95 | |
| num_epoch: 3 | |
| learning_rate_schedule: linear | |
| beta_schedule: linear | |
| epsilon_schedule: linear | |
| network_settings: | |
| normalize: true | |
| hidden_units: 512 | |
| num_layers: 3 | |
| vis_encode_type: simple | |
| memory: null | |
| goal_conditioning_type: hyper | |
| deterministic: false | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.995 | |
| strength: 1.0 | |
| network_settings: | |
| normalize: false | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: null | |
| goal_conditioning_type: hyper | |
| deterministic: false | |
| init_path: null | |
| keep_checkpoints: 5 | |
| checkpoint_interval: 500000 | |
| max_steps: 3000000 | |
| time_horizon: 1000 | |
| summary_freq: 30000 | |
| threaded: false | |
| self_play: null | |
| behavioral_cloning: null | |
| env_settings: | |
| env_path: ./training-envs-executables/linux/Worm/Worm | |
| env_args: null | |
| base_port: 5005 | |
| num_envs: 1 | |
| num_areas: 1 | |
| seed: -1 | |
| max_lifetime_restarts: 10 | |
| restarts_rate_limit_n: 1 | |
| restarts_rate_limit_period_s: 60 | |
| engine_settings: | |
| width: 84 | |
| height: 84 | |
| quality_level: 5 | |
| time_scale: 20 | |
| target_frame_rate: -1 | |
| capture_frame_rate: 60 | |
| no_graphics: true | |
| environment_parameters: null | |
| checkpoint_settings: | |
| run_id: WormPPO1 | |
| initialize_from: null | |
| load_model: false | |
| resume: false | |
| force: false | |
| train_model: false | |
| inference: false | |
| results_dir: results | |
| torch_settings: | |
| device: null | |
| debug: false | |