Adding simple_example* notebooks

9e2d890d · hagrid67 · 1154e8da · 9e2d890d · 9e2d890d · 9e2d890d
Commit 9e2d890d authored 5 years ago by hagrid67
--- a/notebooks/simple_example1_env_from_tuple.ipynb
+++ b/notebooks/simple_example1_env_from_tuple.ipynb
--- a/notebooks/simple_example2_generate_random_rail.ipynb
+++ b/notebooks/simple_example2_generate_random_rail.ipynb
--- a/notebooks/simple_example_3.png
+++ b/notebooks/simple_example_3.png
--- a/notebooks/simple_example_3_manual_control.ipynb
+++ b/notebooks/simple_example_3_manual_control.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Simple Example 3 - Manual Control\n",
+    "This opens a separate window, and a text box in the Jupyter notebook.\n",
+    "\n",
+    "eg Enter `\"0 2 s<enter>\"` to tell agent 0 to step forward, and step the environment.\n",
+    "\n",
+    "You should be able to see the red agent step forward, and get a reward from the env, looking like this:\n",
+    "\n",
+    "`Rewards:  {0: -1.0, 1: -1.0}   [done= {0: False, 1: False, '__all__': False} ]`\n",
+    "\n",
+    "Note that this example is set up to use the straightforward \"PIL\" renderer - without the special SBB artwork!\n",
+    "The agent observations are displayed as squares of varying sizes, with a paler version of the agent colour.  The targets are half-size squares in the full agent colour.\n",
+    "\n",
+    "You can switch to the \"PILSVG\" renderer which is prettier but currently renders the agents one step behind, because it needs to know which way the agent is turning.  This can be confusing if you are debugging step-by-step.\n",
+    "\n",
+    "The image below is what the separate window should look like."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![simple_example_3.png](simple_example_3.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import numpy as np\n",
+    "from flatland.envs.generators import random_rail_generator\n",
+    "from flatland.envs.observations import TreeObsForRailEnv\n",
+    "from flatland.envs.rail_env import RailEnv\n",
+    "from flatland.utils.rendertools import RenderTool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "random.seed(1)\n",
+    "np.random.seed(1)\n",
+    "\n",
+    "env = RailEnv(width=7,\n",
+    "              height=7,\n",
+    "              rail_generator=random_rail_generator(),\n",
+    "              number_of_agents=2,\n",
+    "              obs_builder_object=TreeObsForRailEnv(max_depth=2))\n",
+    "\n",
+    "# Print the observation vector for agent 0\n",
+    "obs, all_rewards, done, _ = env.step({0: 0})\n",
+    "for i in range(env.get_num_agents()):\n",
+    "    env.obs_builder.util_print_obs_subtree(tree=obs[i], num_features_per_node=7)\n",
+    "\n",
+    "env_renderer = RenderTool(env, gl=\"PIL\")\n",
+    "# env_renderer = RenderTool(env, gl=\"PILSVG\")\n",
+    "\n",
+    "env_renderer.renderEnv(show=True, frames=True)\n",
+    "env_renderer.renderEnv(show=True, frames=True)\n",
+    "\n",
+    "print(\"Manual control: s=perform step, q=quit, [agent id] [1-2-3 action] \\\n",
+    "       (turnleft+move, move to front, turnright+move)\")\n",
+    "for step in range(100):\n",
+    "    cmd = input(\">> \")\n",
+    "    cmds = cmd.split(\" \")\n",
+    "\n",
+    "    action_dict = {}\n",
+    "\n",
+    "    i = 0\n",
+    "    while i < len(cmds):\n",
+    "        if cmds[i] == 'q':\n",
+    "            import sys\n",
+    "\n",
+    "            sys.exit()\n",
+    "        elif cmds[i] == 's':\n",
+    "            obs, all_rewards, done, _ = env.step(action_dict)\n",
+    "            action_dict = {}\n",
+    "            print(\"Rewards: \", all_rewards, \"  [done=\", done, \"]\")\n",
+    "        else:\n",
+    "            agent_id = int(cmds[i])\n",
+    "            action = int(cmds[i + 1])\n",
+    "            action_dict[agent_id] = action\n",
+    "            i = i + 1\n",
+    "        i += 1\n",
+    "\n",
+    "    env_renderer.renderEnv(show=True, frames=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "hide_input": false,
+  "kernelspec": {
+   "display_name": "ve367",
+   "language": "python",
+   "name": "ve367"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.7"
+  },
+  "latex_envs": {
+   "LaTeX_envs_menu_present": true,
+   "autoclose": false,
+   "autocomplete": true,
+   "bibliofile": "biblio.bib",
+   "cite_by": "apalike",
+   "current_citInitial": 1,
+   "eqLabelWithNumbers": true,
+   "eqNumInitial": 1,
+   "hotkeys": {
+    "equation": "Ctrl-E",
+    "itemize": "Ctrl-I"
+   },
+   "labels_anchors": false,
+   "latex_user_defs": false,
+   "report_style_numbering": false,
+   "user_envs_cfg": false
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
+%% Cell type:markdown id: tags:
+
+### Simple Example 3 - Manual Control
+This opens a separate window, and a text box in the Jupyter notebook.
+
+eg Enter `"0 2 s<enter>"` to tell agent 0 to step forward, and step the environment.
+
+You should be able to see the red agent step forward, and get a reward from the env, looking like this:
+
+`Rewards:  {0: -1.0, 1: -1.0}   [done= {0: False, 1: False, '__all__': False} ]`
+
+Note that this example is set up to use the straightforward "PIL" renderer - without the special SBB artwork!
+The agent observations are displayed as squares of varying sizes, with a paler version of the agent colour.  The targets are half-size squares in the full agent colour.
+
+You can switch to the "PILSVG" renderer which is prettier but currently renders the agents one step behind, because it needs to know which way the agent is turning.  This can be confusing if you are debugging step-by-step.
+
+The image below is what the separate window should look like.
+
+%% Cell type:markdown id: tags:
+
+![simple_example_3.png](simple_example_3.png)
+
+%% Cell type:code id: tags:
+
+``` python
+import random
+import numpy as np
+from flatland.envs.generators import random_rail_generator
+from flatland.envs.observations import TreeObsForRailEnv
+from flatland.envs.rail_env import RailEnv
+from flatland.utils.rendertools import RenderTool
+```
+
+%% Cell type:code id: tags:
+
+``` python
+random.seed(1)
+np.random.seed(1)
+
+env = RailEnv(width=7,
+              height=7,
+              rail_generator=random_rail_generator(),
+              number_of_agents=2,
+              obs_builder_object=TreeObsForRailEnv(max_depth=2))
+
+# Print the observation vector for agent 0
+obs, all_rewards, done, _ = env.step({0: 0})
+for i in range(env.get_num_agents()):
+    env.obs_builder.util_print_obs_subtree(tree=obs[i], num_features_per_node=7)
+
+env_renderer = RenderTool(env, gl="PIL")
+# env_renderer = RenderTool(env, gl="PILSVG")
+
+env_renderer.renderEnv(show=True, frames=True)
+env_renderer.renderEnv(show=True, frames=True)
+
+print("Manual control: s=perform step, q=quit, [agent id] [1-2-3 action] \
+       (turnleft+move, move to front, turnright+move)")
+for step in range(100):
+    cmd = input(">> ")
+    cmds = cmd.split(" ")
+
+    action_dict = {}
+
+    i = 0
+    while i < len(cmds):
+        if cmds[i] == 'q':
+            import sys
+
+            sys.exit()
+        elif cmds[i] == 's':
+            obs, all_rewards, done, _ = env.step(action_dict)
+            action_dict = {}
+            print("Rewards: ", all_rewards, "  [done=", done, "]")
+        else:
+            agent_id = int(cmds[i])
+            action = int(cmds[i + 1])
+            action_dict[agent_id] = action
+            i = i + 1
+        i += 1
+
+    env_renderer.renderEnv(show=True, frames=True)
+```