update st info

Author: findmyway

notebooks/Chapter01_Tic_Tac_Toe.ipynb

@@ -15,9 +15,7 @@
       " \u001b[90m [31c24e10]\u001b[39m\u001b[37m Distributions v0.22.4\u001b[39m\n",
       " \u001b[90m [91a5bcdd]\u001b[39m\u001b[37m Plots v0.29.1\u001b[39m\n",
       " \u001b[90m [02c1da58]\u001b[39m\u001b[37m ReinforcementLearningAnIntroduction v0.2.0 [`..`]\u001b[39m\n",
-      " \u001b[90m [e575027e]\u001b[39m\u001b[37m ReinforcementLearningBase v0.5.0 [`../../ReinforcementLearningBase.jl`]\u001b[39m\n",
-      " \u001b[90m [de1b191a]\u001b[39m\u001b[37m ReinforcementLearningCore v0.1.0 [`../../ReinforcementLearningCore`]\u001b[39m\n",
-      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.0\u001b[39m\n",
+      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.1\u001b[39m\n",
       " \u001b[90m [f3b207a7]\u001b[39m\u001b[37m StatsPlots v0.12.0\u001b[39m\n",
       " \u001b[90m [2f01184e]\u001b[39m\u001b[37m SparseArrays \u001b[39m\n"
      ]
@@ -201,7 +199,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Then we construct a `MonteCarloLearner` for each player. Here the `MonteCarloLearner` is just a wrapper around the approximator."
+    "And wrap it around a MonteCarloLearner."
    ]
   },
   {
@@ -229,7 +227,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Finally we will create the `MonteCarloAgent`. To create such an agent, we need to provide a `learner` and a `policy`. We already have the learners above. Now let's create a policy.\n",
+    "Then the learner is assemble into a policy.\n",
     "\n",
     "A policy is a mapping from states to actions. Considering that we already have the estimations of states, a simple policy would be checking the estimation of the following up states and select one action which will result to the best state."
    ]

notebooks/Chapter02_Ten_Armed_Testbed.ipynb

@@ -13,9 +13,7 @@
       " \u001b[90m [31c24e10]\u001b[39m\u001b[37m Distributions v0.22.4\u001b[39m\n",
       " \u001b[90m [91a5bcdd]\u001b[39m\u001b[37m Plots v0.29.1\u001b[39m\n",
       " \u001b[90m [02c1da58]\u001b[39m\u001b[37m ReinforcementLearningAnIntroduction v0.2.0 [`..`]\u001b[39m\n",
-      " \u001b[90m [e575027e]\u001b[39m\u001b[37m ReinforcementLearningBase v0.5.0 [`../../ReinforcementLearningBase.jl`]\u001b[39m\n",
-      " \u001b[90m [de1b191a]\u001b[39m\u001b[37m ReinforcementLearningCore v0.1.0 [`../../ReinforcementLearningCore`]\u001b[39m\n",
-      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.0\u001b[39m\n",
+      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.1\u001b[39m\n",
       " \u001b[90m [f3b207a7]\u001b[39m\u001b[37m StatsPlots v0.12.0\u001b[39m\n",
       " \u001b[90m [2f01184e]\u001b[39m\u001b[37m SparseArrays \u001b[39m\n"
      ]

notebooks/Chapter03_Grid_World.ipynb

@@ -13,9 +13,7 @@
       " \u001b[90m [31c24e10]\u001b[39m\u001b[37m Distributions v0.22.4\u001b[39m\n",
       " \u001b[90m [91a5bcdd]\u001b[39m\u001b[37m Plots v0.29.1\u001b[39m\n",
       " \u001b[90m [02c1da58]\u001b[39m\u001b[37m ReinforcementLearningAnIntroduction v0.2.0 [`..`]\u001b[39m\n",
-      " \u001b[90m [e575027e]\u001b[39m\u001b[37m ReinforcementLearningBase v0.5.0 [`../../ReinforcementLearningBase.jl`]\u001b[39m\n",
-      " \u001b[90m [de1b191a]\u001b[39m\u001b[37m ReinforcementLearningCore v0.1.0 [`../../ReinforcementLearningCore`]\u001b[39m\n",
-      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.0\u001b[39m\n",
+      " \u001b[90m [2913bbd2]\u001b[39m\u001b[37m StatsBase v0.32.1\u001b[39m\n",
       " \u001b[90m [f3b207a7]\u001b[39m\u001b[37m StatsPlots v0.12.0\u001b[39m\n",
       " \u001b[90m [2f01184e]\u001b[39m\u001b[37m SparseArrays \u001b[39m\n"
      ]