{
 "cells": [
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "# Active Algorithms",
   "id": "eb9fb4a1a68e633"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "AMLGym implements a random baseline for active learning in fully observable and deterministic environments.",
   "id": "1ac309b575ed4764"
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": "!pip install amlgym",
   "id": "3a2c1c2a35c2e0f2"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Get an input domain with predicate/operator signatures and no preconditions and effects.",
   "id": "774218ec2666c651"
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": [
    "from amlgym.benchmarks import get_domain_path\n",
    "from amlgym.util.util import empty_domain\n",
    "\n",
    "domain = 'blocksworld'\n",
    "domain_ref_path = get_domain_path(domain)\n",
    "input_domain_path = empty_domain(domain_ref_path)"
   ],
   "id": "67f9460df2d696a5"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Create a simulator of a fully observable and deterministic environment.",
   "id": "da80e00d74f127a1"
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": [
    "from unified_planning.shortcuts import SequentialSimulator\n",
    "from unified_planning.io import PDDLReader\n",
    "from amlgym.benchmarks import get_problems_path\n",
    "\n",
    "problem_path = get_problems_path(domain, kind='learning')[0]\n",
    "problem = PDDLReader().parse_problem(domain_ref_path, problem_path)\n",
    "\n",
    "env = SequentialSimulator(problem=problem)"
   ],
   "id": "b9f57982d205380"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Instantiate a random agent and learns a model by acting in the simulated environment for a maximum number of 100 steps. At each step, the agent attempts to execute an action and observes the resulting environment state. Notice that action executions can fail.",
   "id": "6b9bde8ba4fe1329"
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": [
    "from amlgym.algorithms import get_algorithm\n",
    "\n",
    "learner = get_algorithm('RandomAgent', max_steps=40)\n",
    "model, trajectory = learner.learn(env, input_domain_path)"
   ],
   "id": "fd01879bb9546ea3"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "Print the learned model and produced trajectory.",
   "id": "3582699c5af52659"
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": [
    "print(\"##################### Learned model #####################\")\n",
    "print(model)\n",
    "\n",
    "print(\"################# Generated trajectory ##################\")\n",
    "print(trajectory)"
   ],
   "id": "7063d567fa9b9075"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}