parameters: project_name: jaxgmg2_antennaban action: rl rl_action: train lr: 5e-5 alpha: 0.6 discount_rate: 0.98 cheese_loc: any env_layout: open env_rule: "ban:c[10,11], m[11,:]; c[11,10], m[:,11]" mask_type: first_episode use_prev_action: false num_total_env_steps: 10_000_000_000 num_levels: 9600 grad_acc_per_chunk: 5 num_rollout_steps: 64 seed_formula: "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:03d}" ckpt_dir: jaxgmg2_antennaban2 f_str_ckpt: "control_al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}" eval_schedule: "0:1,250:2,500:5,2000:10" log_optimizer_state: true wandb_project: jaxgmg2_antennaban use_wandb: true use_hf: true no_tqdm: true ntfy: david_jaxgmg sweep: - - run_id: 84 - run_id: 87 - run_id: 90 - run_id: 92 - run_id: 93 - run_id: 95 - run_id: 101 - run_id: 102 - run_id: 106 - run_id: 109