{"id":19549085,"url":"https://github.com/ps48/doodle-jump-rl","last_synced_at":"2025-10-08T12:49:19.445Z","repository":{"id":52236168,"uuid":"334493496","full_name":"ps48/Doodle-Jump-RL","owner":"ps48","description":"Game Bot Reinforcement Learning and Adversarial Attack ","archived":false,"fork":false,"pushed_at":"2021-05-04T06:04:57.000Z","size":7765,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-10-04T16:56:59.811Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ps48.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-01-30T19:22:56.000Z","updated_at":"2021-05-04T06:04:59.000Z","dependencies_parsed_at":"2022-08-26T05:41:48.204Z","dependency_job_id":null,"html_url":"https://github.com/ps48/Doodle-Jump-RL","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ps48/Doodle-Jump-RL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ps48%2FDoodle-Jump-RL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ps48%2FDoodle-Jump-RL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ps48%2FDoodle-Jump-RL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ps48%2FDoodle-Jump-RL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ps48","download_url":"https://codeload.github.com/ps48/Doodle-Jump-RL/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ps48%2FDoodle-Jump-RL/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278948019,"owners_count":26073747,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T03:57:53.319Z","updated_at":"2025-10-08T12:49:19.427Z","avatar_url":"https://github.com/ps48.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Doodle-Jump-RL\n## **USC - CSCI 527** Under Prof. Micheal Zyda\nGame Bot Reinforcement Learning and Adversarial Attack \n## [Jump to our webpage](https://pranavmswamy.github.io/doodle-jump-website/)\n\u003cimg src=\"game\\assets\\giphy_end.gif\" width=\"150\" height=\"150\"/\u003e\n\n## Getting Started\n1. Clone the repository\n2. Install the requirements `pip install -r requirements.txt`\n\n## Usage\n* Train/Test **DQN \u0026 DRQN** Model\n```\npython deepQAgent.py\n\n  -h, --help            show this help message and exit\n  --macos               select model to train the agent\n  --human               playing the game manually without agent\n  --test                playing the game with a trained agent\n  -d {EASY,MEDIUM,HARD}, --difficulty {EASY,MEDIUM,HARD}\n                        select difficulty of the game\n  -m {dqn,drqn,resnet,mobilenet,mnasnet}, --model {dqn,drqn,resnet,mobilenet,mnasnet}\n                        select model to train the agent\n  -p MODEL_PATH, --model_path MODEL_PATH\n                        path to weights of an earlier trained model\n  -lr LEARNING_RATE, --learning_rate LEARNING_RATE\n                        set learning rate for training the model\n  -g GAMMA, --gamma GAMMA\n                        set discount factor for q learning\n  --max_memory MAX_MEMORY\n                        Buffer memory size for long training\n  --store_frames        store frames encountered during game play by agent\n  --batch_size BATCH_SIZE\n                        Batch size for long training\n  --reward_type {1,2,3,4,5,6}\n                        types of rewards formulation\n  --exploration EXPLORATION\n                        number of games to explore\n  --channels CHANNELS   set the image channels for preprocessing\n  --height HEIGHT       set the image height post resize\n  --width WIDTH         set the image width post resize\n  --server              when training on server add this flag\n  --seed SEED           change seed value for creating game randomness\n  --max_games MAX_GAMES\n                        set the max number of games to be played by the agent\n  --explore {epsilon_g,epsilon_g_decay_exp,epsilon_g_decay_exp_cur}\n                        select the exploration vs exploitation tradeoff\n  --decay_factor DECAY_FACTOR\n                        set the decay factor for exploration\n  --epsilon EPSILON     set the epsilon value for exploration\n  --attack              use fast fgsm attack to manipulate the input state\n  --attack_eps ATTACK_EPS\n                        epsilon value for the fgsm attack\n```\n* Train/Test **A2C** Model\n```\npython a2cAgent.py --options\n```\n* Train/Test **PPO** Model\n```\npython ppoAgent.py --options\n```\n\n## Folder Tree\n```\nRoot\n|   .gitignore\n|   a2cAgent.py\n|   deepQAgent.py\n|   helper.py\n|   ppoAgent.py\n|   README.md\n|   requirements.txt\n|   rewards.py\n|\n+---game\n|   |   doodlejump.py\n|   |   LICENSE\n|   |   __init__.py\n|   |\n|   \\---assets\n|\n\\---model\n    |   a2cTrainer.py\n    |   deepQTrainer.py\n    |   networks.py\n    |   ppoTrainernew.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fps48%2Fdoodle-jump-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fps48%2Fdoodle-jump-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fps48%2Fdoodle-jump-rl/lists"}