diff --git a/anpcp/igrasp_iters.ipynb b/anpcp/igrasp_iters.ipynb
index acf2147..108bc85 100644
--- a/anpcp/igrasp_iters.ipynb
+++ b/anpcp/igrasp_iters.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -17,12 +17,13 @@
     "from grasp_iters import read_results\n",
     "\n",
     "# iters = read_results(\"rl1323_882_441_0_p44_a3\")\n",
-    "iters = read_results(\"rat783_522_261_0_p20_a2\")"
+    "# iters = read_results(\"rat783_522_261_0_p20_a2\")\n",
+    "iters = read_results(\"rl1323_882_441_0_p20_a3\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -58,47 +59,47 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>0</td>\n",
-       "      <td>0.764880</td>\n",
-       "      <td>130</td>\n",
-       "      <td>128</td>\n",
-       "      <td>0.240514</td>\n",
+       "      <td>0.217888</td>\n",
+       "      <td>5624</td>\n",
+       "      <td>4180</td>\n",
+       "      <td>6.555388</td>\n",
        "      <td>True</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>1</td>\n",
-       "      <td>0.223220</td>\n",
-       "      <td>127</td>\n",
-       "      <td>111</td>\n",
-       "      <td>0.526771</td>\n",
-       "      <td>True</td>\n",
+       "      <td>0.881793</td>\n",
+       "      <td>7000</td>\n",
+       "      <td>4495</td>\n",
+       "      <td>9.334014</td>\n",
+       "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>2</td>\n",
-       "      <td>0.676699</td>\n",
-       "      <td>171</td>\n",
-       "      <td>116</td>\n",
-       "      <td>1.479618</td>\n",
+       "      <td>0.806632</td>\n",
+       "      <td>6841</td>\n",
+       "      <td>4304</td>\n",
+       "      <td>13.462326</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>3</td>\n",
-       "      <td>0.880670</td>\n",
-       "      <td>174</td>\n",
-       "      <td>121</td>\n",
-       "      <td>2.832945</td>\n",
+       "      <td>0.440826</td>\n",
+       "      <td>6538</td>\n",
+       "      <td>4252</td>\n",
+       "      <td>17.854619</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>4</td>\n",
-       "      <td>0.514568</td>\n",
-       "      <td>150</td>\n",
-       "      <td>110</td>\n",
-       "      <td>3.488692</td>\n",
-       "      <td>True</td>\n",
+       "      <td>0.698069</td>\n",
+       "      <td>5828</td>\n",
+       "      <td>4327</td>\n",
+       "      <td>22.075512</td>\n",
+       "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -112,46 +113,46 @@
        "    <tr>\n",
        "      <th>4995</th>\n",
        "      <td>4995</td>\n",
-       "      <td>0.481696</td>\n",
-       "      <td>163</td>\n",
-       "      <td>137</td>\n",
-       "      <td>3194.595398</td>\n",
+       "      <td>0.258762</td>\n",
+       "      <td>7176</td>\n",
+       "      <td>4304</td>\n",
+       "      <td>16058.317987</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4996</th>\n",
        "      <td>4996</td>\n",
-       "      <td>0.761338</td>\n",
-       "      <td>176</td>\n",
-       "      <td>139</td>\n",
-       "      <td>3194.947613</td>\n",
+       "      <td>0.236388</td>\n",
+       "      <td>5918</td>\n",
+       "      <td>4388</td>\n",
+       "      <td>16061.272851</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4997</th>\n",
        "      <td>4997</td>\n",
-       "      <td>0.407531</td>\n",
-       "      <td>140</td>\n",
-       "      <td>118</td>\n",
-       "      <td>3195.208658</td>\n",
+       "      <td>0.045704</td>\n",
+       "      <td>5833</td>\n",
+       "      <td>4327</td>\n",
+       "      <td>16065.256414</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4998</th>\n",
        "      <td>4998</td>\n",
-       "      <td>0.478522</td>\n",
-       "      <td>138</td>\n",
-       "      <td>105</td>\n",
-       "      <td>3196.069135</td>\n",
+       "      <td>0.892714</td>\n",
+       "      <td>7211</td>\n",
+       "      <td>4182</td>\n",
+       "      <td>16069.853268</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4999</th>\n",
        "      <td>4999</td>\n",
-       "      <td>0.082856</td>\n",
-       "      <td>140</td>\n",
-       "      <td>100</td>\n",
-       "      <td>3196.789983</td>\n",
+       "      <td>0.429547</td>\n",
+       "      <td>6037</td>\n",
+       "      <td>4495</td>\n",
+       "      <td>16072.412483</td>\n",
        "      <td>False</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
@@ -160,23 +161,23 @@
        "</div>"
       ],
       "text/plain": [
-       "      iter      beta  RGD_OF  AFVS_OF         time  is_new_best\n",
-       "0        0  0.764880     130      128     0.240514         True\n",
-       "1        1  0.223220     127      111     0.526771         True\n",
-       "2        2  0.676699     171      116     1.479618        False\n",
-       "3        3  0.880670     174      121     2.832945        False\n",
-       "4        4  0.514568     150      110     3.488692         True\n",
-       "...    ...       ...     ...      ...          ...          ...\n",
-       "4995  4995  0.481696     163      137  3194.595398        False\n",
-       "4996  4996  0.761338     176      139  3194.947613        False\n",
-       "4997  4997  0.407531     140      118  3195.208658        False\n",
-       "4998  4998  0.478522     138      105  3196.069135        False\n",
-       "4999  4999  0.082856     140      100  3196.789983        False\n",
+       "      iter      beta  RGD_OF  AFVS_OF          time  is_new_best\n",
+       "0        0  0.217888    5624     4180      6.555388         True\n",
+       "1        1  0.881793    7000     4495      9.334014        False\n",
+       "2        2  0.806632    6841     4304     13.462326        False\n",
+       "3        3  0.440826    6538     4252     17.854619        False\n",
+       "4        4  0.698069    5828     4327     22.075512        False\n",
+       "...    ...       ...     ...      ...           ...          ...\n",
+       "4995  4995  0.258762    7176     4304  16058.317987        False\n",
+       "4996  4996  0.236388    5918     4388  16061.272851        False\n",
+       "4997  4997  0.045704    5833     4327  16065.256414        False\n",
+       "4998  4998  0.892714    7211     4182  16069.853268        False\n",
+       "4999  4999  0.429547    6037     4495  16072.412483        False\n",
        "\n",
        "[5000 rows x 6 columns]"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -187,7 +188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -222,93 +223,66 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>0</td>\n",
-       "      <td>0.764880</td>\n",
-       "      <td>130</td>\n",
-       "      <td>128</td>\n",
-       "      <td>0.240514</td>\n",
+       "      <td>0.217888</td>\n",
+       "      <td>5624</td>\n",
+       "      <td>4180</td>\n",
+       "      <td>6.555388</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1</td>\n",
-       "      <td>0.223220</td>\n",
-       "      <td>127</td>\n",
-       "      <td>111</td>\n",
-       "      <td>0.526771</td>\n",
+       "      <th>9</th>\n",
+       "      <td>9</td>\n",
+       "      <td>0.938647</td>\n",
+       "      <td>8196</td>\n",
+       "      <td>4157</td>\n",
+       "      <td>40.003975</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>4</td>\n",
-       "      <td>0.514568</td>\n",
-       "      <td>150</td>\n",
-       "      <td>110</td>\n",
-       "      <td>3.488692</td>\n",
+       "      <th>66</th>\n",
+       "      <td>66</td>\n",
+       "      <td>0.854831</td>\n",
+       "      <td>7517</td>\n",
+       "      <td>4128</td>\n",
+       "      <td>239.757502</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>8</td>\n",
-       "      <td>0.137148</td>\n",
-       "      <td>130</td>\n",
-       "      <td>100</td>\n",
-       "      <td>6.077239</td>\n",
+       "      <th>76</th>\n",
+       "      <td>76</td>\n",
+       "      <td>0.376441</td>\n",
+       "      <td>5727</td>\n",
+       "      <td>4031</td>\n",
+       "      <td>275.018968</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>11</td>\n",
-       "      <td>0.311568</td>\n",
-       "      <td>157</td>\n",
-       "      <td>98</td>\n",
-       "      <td>8.682613</td>\n",
+       "      <th>180</th>\n",
+       "      <td>180</td>\n",
+       "      <td>0.221051</td>\n",
+       "      <td>5932</td>\n",
+       "      <td>4015</td>\n",
+       "      <td>621.834342</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>19</td>\n",
-       "      <td>0.119498</td>\n",
-       "      <td>160</td>\n",
-       "      <td>95</td>\n",
-       "      <td>17.508947</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>51</th>\n",
-       "      <td>51</td>\n",
-       "      <td>0.189892</td>\n",
-       "      <td>121</td>\n",
-       "      <td>93</td>\n",
-       "      <td>42.765096</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>213</th>\n",
-       "      <td>213</td>\n",
-       "      <td>0.531542</td>\n",
-       "      <td>140</td>\n",
-       "      <td>92</td>\n",
-       "      <td>152.635973</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>947</th>\n",
-       "      <td>947</td>\n",
-       "      <td>0.618655</td>\n",
-       "      <td>131</td>\n",
-       "      <td>91</td>\n",
-       "      <td>633.430784</td>\n",
+       "      <th>3490</th>\n",
+       "      <td>3490</td>\n",
+       "      <td>0.409655</td>\n",
+       "      <td>6261</td>\n",
+       "      <td>3948</td>\n",
+       "      <td>11237.421071</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "     iter      beta  RGD_OF  AFVS_OF        time\n",
-       "0       0  0.764880     130      128    0.240514\n",
-       "1       1  0.223220     127      111    0.526771\n",
-       "4       4  0.514568     150      110    3.488692\n",
-       "8       8  0.137148     130      100    6.077239\n",
-       "11     11  0.311568     157       98    8.682613\n",
-       "19     19  0.119498     160       95   17.508947\n",
-       "51     51  0.189892     121       93   42.765096\n",
-       "213   213  0.531542     140       92  152.635973\n",
-       "947   947  0.618655     131       91  633.430784"
+       "      iter      beta  RGD_OF  AFVS_OF          time\n",
+       "0        0  0.217888    5624     4180      6.555388\n",
+       "9        9  0.938647    8196     4157     40.003975\n",
+       "66      66  0.854831    7517     4128    239.757502\n",
+       "76      76  0.376441    5727     4031    275.018968\n",
+       "180    180  0.221051    5932     4015    621.834342\n",
+       "3490  3490  0.409655    6261     3948  11237.421071"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -320,16 +294,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "9"
+       "6"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -340,37 +314,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0            NaN\n",
-       "1      13.281250\n",
-       "4       0.900901\n",
-       "8       9.090909\n",
-       "11      2.000000\n",
-       "19      3.061224\n",
-       "51      2.105263\n",
-       "213     1.075269\n",
-       "947     1.086957\n",
-       "Name: AFVS_OF, dtype: float64"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "percents = improvs[\"AFVS_OF\"].pct_change().mul(-100)\n",
-    "percents"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -406,119 +350,90 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>0</td>\n",
-       "      <td>0.764880</td>\n",
-       "      <td>130</td>\n",
-       "      <td>128</td>\n",
+       "      <td>0.217888</td>\n",
+       "      <td>5624</td>\n",
+       "      <td>4180</td>\n",
        "      <td>NaN</td>\n",
-       "      <td>0.240514</td>\n",
+       "      <td>6.555388</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1</td>\n",
-       "      <td>0.223220</td>\n",
-       "      <td>127</td>\n",
-       "      <td>111</td>\n",
-       "      <td>13.281250</td>\n",
-       "      <td>0.526771</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>4</td>\n",
-       "      <td>0.514568</td>\n",
-       "      <td>150</td>\n",
-       "      <td>110</td>\n",
-       "      <td>0.900901</td>\n",
-       "      <td>3.488692</td>\n",
+       "      <th>9</th>\n",
+       "      <td>9</td>\n",
+       "      <td>0.938647</td>\n",
+       "      <td>8196</td>\n",
+       "      <td>4157</td>\n",
+       "      <td>0.550239</td>\n",
+       "      <td>40.003975</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>8</td>\n",
-       "      <td>0.137148</td>\n",
-       "      <td>130</td>\n",
-       "      <td>100</td>\n",
-       "      <td>9.090909</td>\n",
-       "      <td>6.077239</td>\n",
+       "      <th>66</th>\n",
+       "      <td>66</td>\n",
+       "      <td>0.854831</td>\n",
+       "      <td>7517</td>\n",
+       "      <td>4128</td>\n",
+       "      <td>0.697618</td>\n",
+       "      <td>239.757502</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>11</td>\n",
-       "      <td>0.311568</td>\n",
-       "      <td>157</td>\n",
-       "      <td>98</td>\n",
-       "      <td>2.000000</td>\n",
-       "      <td>8.682613</td>\n",
+       "      <th>76</th>\n",
+       "      <td>76</td>\n",
+       "      <td>0.376441</td>\n",
+       "      <td>5727</td>\n",
+       "      <td>4031</td>\n",
+       "      <td>2.349806</td>\n",
+       "      <td>275.018968</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>19</td>\n",
-       "      <td>0.119498</td>\n",
-       "      <td>160</td>\n",
-       "      <td>95</td>\n",
-       "      <td>3.061224</td>\n",
-       "      <td>17.508947</td>\n",
+       "      <th>180</th>\n",
+       "      <td>180</td>\n",
+       "      <td>0.221051</td>\n",
+       "      <td>5932</td>\n",
+       "      <td>4015</td>\n",
+       "      <td>0.396924</td>\n",
+       "      <td>621.834342</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>51</th>\n",
-       "      <td>51</td>\n",
-       "      <td>0.189892</td>\n",
-       "      <td>121</td>\n",
-       "      <td>93</td>\n",
-       "      <td>2.105263</td>\n",
-       "      <td>42.765096</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>213</th>\n",
-       "      <td>213</td>\n",
-       "      <td>0.531542</td>\n",
-       "      <td>140</td>\n",
-       "      <td>92</td>\n",
-       "      <td>1.075269</td>\n",
-       "      <td>152.635973</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>947</th>\n",
-       "      <td>947</td>\n",
-       "      <td>0.618655</td>\n",
-       "      <td>131</td>\n",
-       "      <td>91</td>\n",
-       "      <td>1.086957</td>\n",
-       "      <td>633.430784</td>\n",
+       "      <th>3490</th>\n",
+       "      <td>3490</td>\n",
+       "      <td>0.409655</td>\n",
+       "      <td>6261</td>\n",
+       "      <td>3948</td>\n",
+       "      <td>1.668742</td>\n",
+       "      <td>11237.421071</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "     iter      beta  RGD_OF  AFVS_OF        imp        time\n",
-       "0       0  0.764880     130      128        NaN    0.240514\n",
-       "1       1  0.223220     127      111  13.281250    0.526771\n",
-       "4       4  0.514568     150      110   0.900901    3.488692\n",
-       "8       8  0.137148     130      100   9.090909    6.077239\n",
-       "11     11  0.311568     157       98   2.000000    8.682613\n",
-       "19     19  0.119498     160       95   3.061224   17.508947\n",
-       "51     51  0.189892     121       93   2.105263   42.765096\n",
-       "213   213  0.531542     140       92   1.075269  152.635973\n",
-       "947   947  0.618655     131       91   1.086957  633.430784"
+       "      iter      beta  RGD_OF  AFVS_OF       imp          time\n",
+       "0        0  0.217888    5624     4180       NaN      6.555388\n",
+       "9        9  0.938647    8196     4157  0.550239     40.003975\n",
+       "66      66  0.854831    7517     4128  0.697618    239.757502\n",
+       "76      76  0.376441    5727     4031  2.349806    275.018968\n",
+       "180    180  0.221051    5932     4015  0.396924    621.834342\n",
+       "3490  3490  0.409655    6261     3948  1.668742  11237.421071"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "percents = improvs[\"AFVS_OF\"].pct_change().mul(-100)\n",
     "improvs.insert(loc=4, column=\"imp\", value=percents)\n",
     "improvs"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 1440x360 with 1 Axes>"
       ]
diff --git a/anpcp/nb_results/grasp/iters_rl1323_882_441_0_p20_a3.pkl b/anpcp/nb_results/grasp/iters_rl1323_882_441_0_p20_a3.pkl
new file mode 100644
index 0000000..4017eb0
Binary files /dev/null and b/anpcp/nb_results/grasp/iters_rl1323_882_441_0_p20_a3.pkl differ