{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"2022-01-24-advertising.ipynb","provenance":[{"file_id":"https://github.com/recohut/nbs/blob/main/raw/T256744%20%7C%20Real-Time%20Bidding%20in%20Advertising.ipynb","timestamp":1644669406997}],"collapsed_sections":[],"authorship_tag":"ABX9TyN2zv1P3AB6lhIE+N9qIwxe"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"markdown","metadata":{"id":"fEheFRY2RVTh"},"source":["# Real-Time Bidding in Advertising"]},{"cell_type":"markdown","metadata":{"id":"cPxQk26hRaCC"},"source":["Contrary to sponsored advertising, where advertisers set fixed bids, in real-time bid‐ ding (RTB) you can set a bid for every individual impression. When a user visits a website that supports ads, this triggers an auction where advertisers bid for an impres‐ sion. Advertisers must submit bids within a period of time, where 100 ms is a com‐ mon limit.\n","\n","The advertising platform provides contextual and behavioral information to the advertiser for evaluation. The advertiser uses an automated algorithm to decide how much to bid based upon the context. In the long-term, the platform’s products must deliver a satisfying experience, to maintain the advertising revenue stream. But adver‐ tisers want to maximize some key performance indicator (KPI), for example, the number of impressions or click through rate (CTR), for the least cost.\n","\n","RTB presents a clear action (the bid), state (the information provided by the plat‐ form) and agent (the bidding algorithm). Both platforms and advertisers can use RL to optimize for their definition of reward.\n","\n","To quickly demonstrate this idea, below I present some code to simulate a bidding environment. First let me install the dependencies."]},{"cell_type":"markdown","metadata":{"id":"KeEWIEeNRd1f"},"source":["## Setup"]},{"cell_type":"code","metadata":{"id":"vjjJfROzRdxD"},"source":["!pip install pygame==1.9.6 pandas==1.0.5 matplotlib==3.2.1 gym==0.17.3 gym-display-advertising==0.0.1\n","!pip install --upgrade git+git://github.com/david-abel/simple_rl.git@77c0d6b910efbe8bdd5f4f87337c5bc4aed0d79c"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"4yA4L7P0Riqa"},"source":["import numpy as np\n","import pandas as pd\n","\n","from simple_rl.agents import RandomAgent, DelayedQAgent, DoubleQAgent, QLearningAgent\n","\n","import gym\n","import gym_display_advertising\n","\n","import matplotlib\n","import matplotlib.pyplot as plt\n","matplotlib.use(\"agg\", force=True)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"loyZk1M-Rin1"},"source":["%matplotlib inline"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"3M4uQhDqRill"},"source":["## Params"]},{"cell_type":"code","metadata":{"id":"HT0ERwAwRijW"},"source":["eps = 0.05\n","gam = 0.99\n","alph = 0.0001\n","n_episodes = 200"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"AHNGVWECR1e1"},"source":["## Utils"]},{"cell_type":"markdown","metadata":{"id":"URQQCQ9QR5Ru"},"source":["This section contains quite a lot of code. These are the helper functions to perform various aspects of the problem. For example, I need to discretize the state space so that it works with the tabular value-based algorithms.\n","\n","Then there is some helper code to perform the training iteration. Loops in loops."]},{"cell_type":"code","metadata":{"id":"c7z8WxB2R511"},"source":["def state_mapping(obs):\n","    \"\"\"\n","    Since this is tabular, we can't use real numbers. There would be an infinite\n","    number of states. Instead I round and convert to an integer. This is a\n","    simple form of _tile coding_.\n","    \"\"\"\n","    return tuple(np.round(100 * obs[0:1]))\n","\n","def run_episode(env, agent, learning=True):\n","    episode_reward = 0\n","    observation = env.reset()\n","    episode_over = False\n","    reward = 0\n","    action_buffer = []\n","    while not episode_over:\n","        if hasattr(agent, \"q_func\"):\n","            action = agent.act(\n","                state_mapping(observation),\n","                reward,\n","                learning=learning)\n","        else:\n","            action = agent.act(\n","                state_mapping(observation),\n","                reward)\n","        action_buffer.append(observation[0])\n","        observation, reward, episode_over, _ = env.step(action)\n","        episode_reward += reward\n","    agent.end_of_episode()\n","    return episode_reward, action_buffer\n","\n","def train_agent(env, agent_func, n_repeats):\n","    train_rewards_buffer = np.zeros((n_episodes, n_repeats))\n","    train_bid_buffer = np.zeros((n_episodes, n_repeats, env.batch_size))\n","    for instance in range(n_repeats):\n","        agent = agent_func(range(env.action_space.n))\n","        for episode in range(n_episodes):\n","            episode_reward, action_buffer = run_episode(env, agent)\n","            train_rewards_buffer[episode, instance] = episode_reward\n","            train_bid_buffer[episode, instance, :] = np.pad(\n","                action_buffer, (0, env.batch_size - len(action_buffer)),\n","                'constant', constant_values=0)\n","\n","    if hasattr(agent, \"q_func\"):\n","        print_arbitrary_policy(agent.q_func)\n","\n","    # Test\n","    agent.epsilon = 0\n","    episode_reward, test_bid_buffer = run_episode(env, agent, learning=False)\n","    print(\n","        \"{}: {}\".format(\n","            \"TEST\",\n","            episode_reward))\n","    print(train_rewards_buffer.transpose())\n","    print(test_bid_buffer)\n","    return train_rewards_buffer, train_bid_buffer.mean(axis=2)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"3RUIDX2HSM9-"},"source":["def average(data):\n","    return pd.DataFrame(data.mean(axis=1))\n","\n","def save(df, path):\n","    df.to_json(path)\n","\n","def print_arbitrary_policy(Q):\n","    for state in sorted(Q.keys(), key=lambda x: (x is None, x)):\n","        values = Q[state].items()\n","        print(\"{}: {}\".format(state, sorted(values)))"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"JOGQf6x5SHBf"},"source":["## Agent"]},{"cell_type":"code","metadata":{"id":"HQOpYBmTSIDO"},"source":["def q_agent(actions):\n","    return QLearningAgent(\n","        actions,\n","        gamma=gam,\n","        epsilon=eps,\n","        alpha=alph,\n","    )\n","\n","def random_agent(actions):\n","    return RandomAgent(actions)\n","\n","\n","def sarsa_agent(actions):\n","    return SARSAAgent(actions, 999, gamma=gam, epsilon=eps, alpha=alph, )"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"mqmyA5ftSKDE"},"source":["## Running the Experiment\n","Finally I’m going to run the experiments. I also print a lot of debugging so you can see the raw Q-values. I encourage you to inspect these, and investigate how this changes through learning."]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"zkeNn9paSROB","executionInfo":{"status":"ok","timestamp":1634457974989,"user_tz":-330,"elapsed":14977,"user":{"displayName":"Sparsh Agarwal","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"13037694610922482904"}},"outputId":"30b19f94-d5e7-4324-8954-1a76c31a098b"},"source":["name = \"bidding_rl_delta_q_learning\"\n","env_name = \"StaticDisplayAdvertising-v0\"\n","num_repeats = 10\n","agent = q_agent\n","print(\"Starting {}\".format(name))\n","env = gym.make(env_name)\n","rewards_buffer, bid_buffer = train_agent(env, agent, num_repeats)\n","save(average(rewards_buffer), name + \".json\")\n","save(average(bid_buffer), name + \"_bid.json\")\n","print(\"Stopping {}\".format(name))"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Starting bidding_rl_delta_q_learning\n","(0.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(1.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(2.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(3.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(4.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(5.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 1.5986184241244227e-16)]\n","(6.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 2.9767579532479464e-17)]\n","(7.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 2.1017160764932272e-12)]\n","(8.0,): [(0, 0.0), (1, 2.937298888795957e-16), (2, 0.0), (3, 0.0), (4, 0.0), (5, 0.0), (6, 0.0)]\n","(9.0,): [(0, 0.0), (1, 0), (2, 0.0), (3, 0.0), (4, 0.0), (5, 7.863725940834891e-13), (6, 0)]\n","(10.0,): [(0, 0.0), (1, 0.0), (2, 7.683171571207736e-20), (3, 3.385530538584227e-13), (4, 0.0), (5, 3.4611686752791275e-09), (6, 0.0)]\n","(11.0,): [(0, 0.0), (1, 9.558765177717925e-16), (2, 0.0), (3, 3.925213342567121e-13), (4, 1.1864155088453227e-12), (5, 1.1487337936278007e-07), (6, 2.1334634731235385e-10)]\n","(12.0,): [(0, 0.0), (1, 0), (2, 0.0), (3, 2.169797603618152e-09), (4, 5.238053608921087e-10), (5, 0.0), (6, 2.861207259076816e-05)]\n","(13.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0.0), (5, 0), (6, 0.00019348380980921889)]\n","(14.0,): [(0, 0), (1, 0.0), (2, 7.124021415011489e-10), (3, 0.0), (4, 1.2848041263229343e-10), (5, 1.5201707084878288e-10), (6, 0.0024657147527178034)]\n","(15.0,): [(0, 0.0), (1, 0.0), (2, 0), (3, 0), (4, 5.389611359550401e-06), (5, 0), (6, 0)]\n","(16.0,): [(0, 0.0), (1, 1.8921861445448376e-07), (2, 0), (3, 0), (4, 0), (5, 0.0), (6, 0.004610079904908892)]\n","(17.0,): [(0, 0.0), (1, 0.0), (2, 0.0), (3, 0.0), (4, 0), (5, 2.8823350348146305e-05), (6, 0.0006066167548883614)]\n","(18.0,): [(0, 1.4946323954474337e-17), (1, 6.047239739208024e-07), (2, 2.1096681193744704e-09), (3, 6.92846221865187e-08), (4, 2.58122203640065e-06), (5, 0.0060658262392547305), (6, 0)]\n","(19.0,): [(0, 4.440622564443755e-17), (1, 5.470419049657874e-07), (2, 1.4194100076143626e-06), (3, 3.9121732075389835e-06), (4, 0.0001001784086509009), (5, 0.025790050471078803), (6, 0.00020053623088479917)]\n","(20.0,): [(0, 2.5190132994218816e-12), (1, 2.3229604384118518e-05), (2, 3.899819647396959e-05), (3, 0.0009503177107922988), (4, 0.28819599250118233), (5, 0.00182065979608774), (6, 0.0022094835647729788)]\n","(21.0,): [(0, 4.07978856602482e-11), (1, 5.058889331997783e-05), (2, 0.15173186379013745), (3, 0.0029137067742536224), (4, 0.0031171609808562516), (5, 0.001902799298912826), (6, 0.00249768214882832)]\n","(22.0,): [(0, 0.0), (1, 0), (2, 0.015426124387019796), (3, 0.00010078070953049689), (4, 0.0001008141400611908), (5, 0.0002007620791866908), (6, 0)]\n","(23.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0.004216286889076344), (6, 0)]\n","(24.0,): [(0, 4.896174202132625e-10), (1, 0), (2, 0.00010007925305323805), (3, 0), (4, 0.010099827827821083), (5, 0.00010014893771066539), (6, 0.00010031667860332133)]\n","(25.0,): [(0, 0), (1, 0.00010009960891082659), (2, 0), (3, 0), (4, 0.0001005846869236042), (5, 0.014043641898698918), (6, 0.00020215776493054285)]\n","(26.0,): [(0, 0), (1, 0), (2, 0.008613994852213456), (3, 0), (4, 0.00010022929597136172), (5, 0), (6, 0.00010018904273016812)]\n","(27.0,): [(0, 2.6031070835389265e-07), (1, 0.0005042827601518867), (2, 0.00010010890248265988), (3, 0), (4, 0), (5, 0.0002008228932544119), (6, 0.017855431591600142)]\n","(28.0,): [(0, 2.2273832608930657e-06), (1, 0.0019140773652747219), (2, 0.001308096014059514), (3, 0.2182074069454753), (4, 0.0016007805238050967), (5, 0.001302907928894972), (6, 0.001010604942708029)]\n","(29.0,): [(0, 0), (1, 0), (2, 0.003162974819583311), (3, 0), (4, 0.00010017825314349963), (5, 0.00010008913487355903), (6, 0)]\n","(30.0,): [(0, 9.572112043379467e-10), (1, 0.011644321561148821), (2, 0), (3, 0.0002014589850891427), (4, 0.00020009893226886373), (5, 0.00010000003041687818), (6, 0)]\n","(31.0,): [(0, 2.3891165651271934e-06), (1, 0.00023600617369892116), (2, 0), (3, 0.00010017825314349963), (4, 0), (5, 0.002200472489744916), (6, 0)]\n","(32.0,): [(0, 0.0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0.00010000007590782745), (6, 0.0013007429751292585)]\n","(33.0,): [(0, 1.0906650653822107e-06), (1, 0), (2, 0), (3, 0), (4, 1.4241132538663945e-10), (5, 3.661444710925897e-07), (6, 0)]\n","(34.0,): [(0, 0), (1, 0.0026112081102226854), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(35.0,): [(0, 1.4983320073365203e-06), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(36.0,): [(0, 0), (1, 0.00010004950774456996), (2, 0), (3, 0.00010049466752330035), (4, 0), (5, 0), (6, 0.003997930612608225)]\n","(37.0,): [(0, 3.436782022501716e-06), (1, 0.00019995025428245792), (2, 0.0005997907153505415), (3, 0.058072233225188126), (4, 0.0005042449342761901), (5, 0.0009804148385238257), (6, 0.00020047619226734722)]\n","(38.0,): [(0, 1.3478838240934523e-06), (1, 0), (2, 0.006216906936272676), (3, 0.0001005532816692978), (4, 0.00010919964392670323), (5, 0), (6, 0.0001)]\n","(39.0,): [(0, 7.4393102662255105e-06), (1, 0.0001000000749269613), (2, 0.0002124685669219098), (3, 0.00020204261217701285), (4, 0.03330403969292585), (5, 0.00020006613017916548), (6, 0.00010022860280310472)]\n","(40.0,): [(0, 0.0019668257458606625), (1, 0.0006018072054467757), (2, 0.0012072469128189829), (3, 0.16185356405028956), (4, 0.0021994102911465866), (5, 0.0016998053928706566), (6, 0.001502311877657156)]\n","(41.0,): [(0, 0.0004516973448730999), (1, 0.0004115377752703198), (2, 0.035998466629186), (3, 0), (4, 0.00010002144203520524), (5, 0.00020002960781116428), (6, 0.00030030686132668475)]\n","(42.0,): [(0, 0.00010159003534500829), (1, 0.002409133998153044), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0.0001)]\n","(43.0,): [(0, 0.0006678661955772906), (1, 0.00010177238252570789), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(44.0,): [(0, 0.001511199210282052), (1, 0), (2, 0), (3, 1.980293805414213e-08), (4, 0), (5, 0), (6, 0)]\n","(45.0,): [(0, 0), (1, 7.172763282268792e-06), (2, 0), (3, 0), (4, 0), (5, 0.001100627986577247), (6, 0)]\n","(46.0,): [(0, 0), (1, 0.00010007922986307778), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(47.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0.0030010394268519184), (5, 0.0001), (6, 0)]\n","(48.0,): [(0, 0), (1, 9.973790352670024e-09), (2, 0), (3, 0), (4, 0.0025015773579352227), (5, 0), (6, 0)]\n","(49.0,): [(0, 0), (1, 0), (2, 0.00020013852521863395), (3, 0.00010013877337162042), (4, 0), (5, 0.0018033917624542984), (6, 0)]\n","(50.0,): [(0, 0), (1, 0), (2, 0.00439645674010904), (3, 0.0001003561657243894), (4, 0), (5, 0), (6, 0)]\n","(51.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0.000499959406)]\n","(52.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0.0002003562630508606), (5, 0), (6, 0)]\n","(53.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 9.902941461308811e-09), (5, 0), (6, 0)]\n","(54.0,): [(0, 0), (1, 0), (2, 0.0001999999039214536), (3, 0), (4, 0.000199989902960102), (5, 0.004299683736341352), (6, 0)]\n","(55.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0.0027080430194056375), (6, 0)]\n","(56.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0.00010002971173039202), (5, 0), (6, 0)]\n","(57.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0.00030005909100506474), (6, 0.0)]\n","(58.0,): [(0, 0), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0.0003999796127781386), (6, 0)]\n","(59.0,): [(0, 0.0024120030072631933), (1, 0.0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(60.0,): [(0, 0.00592102694493925), (1, 3.860615955335337e-07), (2, 0.00020000980390991215), (3, 5.062314493971578e-07), (4, 3.9594066132711665e-08), (5, 0), (6, 0)]\n","(61.0,): [(0, 0.00010002971080472114), (1, 0.001401505222238687), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(63.0,): [(0, 0.0005001769810456419), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(64.0,): [(0, 0), (1, 0), (2, 0.0003001383903819786), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(65.0,): [(0, 0), (1, 0.00040016818652469446), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(72.0,): [(0, 0), (1, 0.0003999994196520371), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(76.0,): [(0, 0), (1, 0), (2, 0.00039999940000078814), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(77.0,): [(0, 0), (1, 0), (2, 0), (3, 0.0012999103030588307), (4, 0.0), (5, 0), (6, 0)]\n","(80.0,): [(0, 1.2472586490627816e-06), (1, 0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","(85.0,): [(0, 0), (1, 0.0), (2, 0), (3, 0), (4, 0), (5, 0), (6, 0)]\n","TEST: 71\n","[[ 0. 42. 64. ... 44. 62. 54.]\n"," [36. 65. 27. ... 81. 75. 85.]\n"," [ 0. 39. 74. ... 45. 45. 42.]\n"," ...\n"," [ 3. 17. 40. ... 71. 67. 58.]\n"," [ 0.  0.  0. ... 61. 61. 40.]\n"," [ 1.  0.  1. ... 77. 49.  0.]]\n","[0.2300021626161211, 0.25300237887773325, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655, 0.27830261676550655]\n","Stopping bidding_rl_delta_q_learning\n"]}]},{"cell_type":"markdown","metadata":{"id":"9mPxoc8DSTuk"},"source":["Next I run the same code again but this time with the random agent."]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Ss0_524HSZFe","executionInfo":{"status":"ok","timestamp":1634457991971,"user_tz":-330,"elapsed":8772,"user":{"displayName":"Sparsh Agarwal","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"13037694610922482904"}},"outputId":"a51a5de0-5629-448c-9c1d-9fe8d0de687a"},"source":["name = \"bidding_rl_delta_random\"\n","env_name = \"StaticDisplayAdvertising-v0\"\n","num_repeats = 10\n","agent = random_agent\n","print(\"Starting {}\".format(name))\n","env = gym.make(env_name)\n","rewards_buffer, bid_buffer = train_agent(env, agent, num_repeats)\n","save(average(rewards_buffer), name + \".json\")\n","save(average(bid_buffer), name + \"_bid.json\")\n","print(\"Stopping {}\".format(name))"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Starting bidding_rl_delta_random\n","TEST: 1\n","[[ 0. 10.  4. ... 19. 51. 48.]\n"," [ 0.  0. 13. ... 19.  0.  2.]\n"," [ 0.  0.  0. ... 10. 12. 12.]\n"," ...\n"," [ 6.  1.  1. ... 35. 14.  3.]\n"," [ 6. 18. 12. ...  5. 25.  1.]\n"," [ 0.  0.  0. ... 16.  0.  1.]]\n","[0.28246021011155464, 0.26833719960597696, 0.13416859980298848, 0.1408770297931379, 0.1267893268138241, 0.13946825949520653, 0.1534150854447272, 0.0767075427223636, 0.0383537713611818, 0.0383537713611818, 0.04027145992924089, 0.04027145992924089, 0.04027145992924089, 0.020135729964620444, 0.02114251646285147, 0.010571258231425735, 0.005285629115712867, 0.0026428145578564336, 0.003964221836784651, 0.004360644020463115, 0.003924579618416804, 0.005886869427625206, 0.005592525956243945, 0.005592525956243945, 0.005872152254056143, 0.006459367479461757, 0.006782335853434846, 0.003391167926717423, 0.003221609530381552, 0.003221609530381552, 0.002899448577343397, 0.0014497242886716984, 0.0014497242886716984, 0.002174586433007548, 0.001957127789706793, 0.0009785638948533965, 0.0008807075053680569, 0.00044035375268402843, 0.0004843891279524313, 0.0004843891279524313, 0.0004359502151571882, 0.0004359502151571882, 0.0003923551936414694, 0.0003923551936414694, 0.0001961775968207347, 0.00029426639523110203, 0.00027955307546954694, 0.00027955307546954694, 0.00029353072924302433, 0.00029353072924302433, 0.00014676536462151216, 0.00022014804693226825, 0.00011007402346613412, 9.906662111952071e-05, 4.953331055976036e-05, 7.429996583964055e-05, 8.172996242360461e-05, 7.355696618124415e-05, 6.620126956311975e-05, 9.930190434467963e-05, 4.9650952172339815e-05, 4.9650952172339815e-05, 7.447642825850972e-05, 8.19240710843607e-05, 7.373166397592463e-05, 7.741824717472087e-05, 7.354733481598483e-05, 6.986996807518558e-05, 6.637646967142629e-05, 5.973882270428367e-05, 5.973882270428367e-05, 6.272576383949784e-05, 6.586205203147275e-05, 5.927584682832547e-05, 5.3348262145492926e-05, 2.6674131072746463e-05, 2.4006717965471818e-05, 2.2806382067198227e-05, 2.394670117055814e-05, 2.1552031053502322e-05, 3.232804658025348e-05, 4.849206987038022e-05, 4.606746637686121e-05, 4.837083969570427e-05, 4.353375572613385e-05, 4.7887131298747235e-05, 7.183069694812086e-05, 7.183069694812086e-05, 7.901376664293296e-05, 3.950688332146648e-05, 4.345757165361313e-05, 6.518635748041969e-05, 9.777953622062954e-05, 8.80015825985666e-05, 4.40007912992833e-05, 4.40007912992833e-05, 2.200039564964165e-05, 1.9800356084677485e-05, 2.1780391693145236e-05, 1.0890195846572618e-05]\n","Stopping bidding_rl_delta_random\n"]}]},{"cell_type":"markdown","metadata":{"id":"KnaOI6MoSZYr"},"source":["## Results\n","\n","In the next two plots I present the sum of the rewards in an episode, over 200 episode, averaged over 10 runs. You’d need to perform more averaging to the the plots smoother.\n","\n","You can see that the RL based agent quickly learns where to position the bid amount in order to maximize the reward.\n","\n","The second image shows the bid amount changes over time."]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":279},"id":"DCwhjBgASeD_","executionInfo":{"status":"ok","timestamp":1634458008801,"user_tz":-330,"elapsed":739,"user":{"displayName":"Sparsh Agarwal","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"13037694610922482904"}},"outputId":"e0725d21-2727-4705-d6ca-599e0f99665e"},"source":["data_files = [(\"Random\", \"bidding_rl_delta_random.json\"),\n","              (\"Q-Learning\", \"bidding_rl_delta_q_learning.json\")]\n","\n","fig, ax = plt.subplots()\n","for j, (name, data_file) in enumerate(data_files):\n","    df = pd.read_json(data_file)\n","    x = range(len(df))\n","    y = df.sort_index().values\n","    ax.plot(x,\n","            y,\n","            linestyle='solid',\n","            label=name)\n","ax.set_xlabel('Episode')\n","ax.set_ylabel('Averaged Sum of Rewards')\n","ax.legend(loc='lower right')\n","plt.show()"],"execution_count":null,"outputs":[{"output_type":"display_data","data":{"image/png":"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\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":279},"id":"4BNeTMucSfbZ","executionInfo":{"status":"ok","timestamp":1634458014176,"user_tz":-330,"elapsed":736,"user":{"displayName":"Sparsh Agarwal","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"13037694610922482904"}},"outputId":"1c7fe82f-918e-47f8-c09c-8980c3463770"},"source":["data_files = [(\"Random\", \"bidding_rl_delta_random_bid.json\"),\n","              (\"Q-Learning\", \"bidding_rl_delta_q_learning_bid.json\")]\n","\n","fig, ax = plt.subplots()\n","for j, (name, data_file) in enumerate(data_files):\n","    df = pd.read_json(data_file)\n","    x = range(len(df))\n","    y = df.sort_index().values\n","    ax.plot(x,\n","            y,\n","            linestyle='solid',\n","            label=name)\n","ax.set_xlabel('Episode')\n","ax.set_ylabel('Advertising bid')\n","ax.legend(loc='lower right')\n","plt.show()"],"execution_count":null,"outputs":[{"output_type":"display_data","data":{"image/png":"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\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"needs_background":"light"}}]}]}