metrics.json

{
  "step": 1000,
  "metrics": {
    "eval_rew_align/success_auprc_robotsmith": 0.7499203111579319,
    "eval_rew_align/positive_success_acc_robotsmith": 0.9166666666666666,
    "eval_rew_align/negative_success_acc_robotsmith": 0.9577464788732394,
    "eval_rew_align/loss_robotsmith": 4.106191897392273,
    "eval_rew_align/pearson_robotsmith": 0.9856438673457457,
    "eval_p_rank/kendall_last_robotsmith": 0.5733333333333333,
    "eval_p_rank/kendall_rewind_last_robotsmith": 1.0,
    "eval_p_rank/avg_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
    "eval_p_rank/min_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
    "eval_p_rank/max_succ_subopt_diff_last_robotsmith": 0.003038907051086448,
    "eval_p_rank/avg_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
    "eval_p_rank/min_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
    "eval_p_rank/max_subopt_fail_diff_last_robotsmith": 0.21372997760772705,
    "eval_p_rank/avg_succ_fail_diff_last_robotsmith": 0.2167688846588135,
    "eval_p_rank/min_succ_fail_diff_last_robotsmith": 0.2167688846588135,
    "eval_p_rank/max_succ_fail_diff_last_robotsmith": 0.2167688846588135,
    "eval_p_rank/ranking_acc_last_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_all_pairs_last_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_failure_vs_successful_last_robotsmith": 0.88,
    "eval_p_rank/ranking_acc_failure_vs_suboptimal_last_robotsmith": 0.92,
    "eval_p_rank/ranking_acc_suboptimal_vs_successful_last_robotsmith": 0.56,
    "eval_p_rank/kendall_avg_robotsmith": 0.5733333333333333,
    "eval_p_rank/kendall_rewind_avg_robotsmith": 1.0,
    "eval_p_rank/avg_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
    "eval_p_rank/min_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
    "eval_p_rank/max_succ_subopt_diff_avg_robotsmith": 0.003038907051086448,
    "eval_p_rank/avg_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
    "eval_p_rank/min_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
    "eval_p_rank/max_subopt_fail_diff_avg_robotsmith": 0.21372997760772705,
    "eval_p_rank/avg_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
    "eval_p_rank/min_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
    "eval_p_rank/max_succ_fail_diff_avg_robotsmith": 0.2167688846588135,
    "eval_p_rank/ranking_acc_avg_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_all_pairs_avg_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_failure_vs_successful_avg_robotsmith": 0.88,
    "eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_robotsmith": 0.92,
    "eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_robotsmith": 0.56,
    "eval_p_rank/kendall_sum_robotsmith": 0.5733333333333333,
    "eval_p_rank/kendall_rewind_sum_robotsmith": 1.0,
    "eval_p_rank/avg_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
    "eval_p_rank/min_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
    "eval_p_rank/max_succ_subopt_diff_sum_robotsmith": 0.003038907051086448,
    "eval_p_rank/avg_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
    "eval_p_rank/min_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
    "eval_p_rank/max_subopt_fail_diff_sum_robotsmith": 0.21372997760772705,
    "eval_p_rank/avg_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
    "eval_p_rank/min_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
    "eval_p_rank/max_succ_fail_diff_sum_robotsmith": 0.2167688846588135,
    "eval_p_rank/ranking_acc_sum_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_all_pairs_sum_robotsmith": 0.7866666666666666,
    "eval_p_rank/ranking_acc_failure_vs_successful_sum_robotsmith": 0.88,
    "eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_robotsmith": 0.92,
    "eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_robotsmith": 0.56,
    "time/custom_evaluations": 43.09463632851839
  }
}