{"id":13839702,"url":"https://github.com/angelmtenor/RL-ROBOT","last_synced_at":"2025-07-11T06:31:21.524Z","repository":{"id":13155431,"uuid":"73743757","full_name":"angelmtenor/RL-ROBOT","owner":"angelmtenor","description":"Reinforcement Learning framework for Robotics","archived":false,"fork":false,"pushed_at":"2022-06-19T16:20:34.000Z","size":6830,"stargazers_count":86,"open_issues_count":0,"forks_count":29,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-11-18T16:45:51.992Z","etag":null,"topics":["cognitive-robotics","decision-making","reinforcement-learning","robotics","ros","v-rep"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/angelmtenor.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-11-14T20:21:42.000Z","updated_at":"2024-11-04T02:40:00.000Z","dependencies_parsed_at":"2022-08-24T03:10:36.438Z","dependency_job_id":null,"html_url":"https://github.com/angelmtenor/RL-ROBOT","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angelmtenor%2FRL-ROBOT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angelmtenor%2FRL-ROBOT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angelmtenor%2FRL-ROBOT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angelmtenor%2FRL-ROBOT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/angelmtenor","download_url":"https://codeload.github.com/angelmtenor/RL-ROBOT/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225700007,"owners_count":17510435,"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","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":["cognitive-robotics","decision-making","reinforcement-learning","robotics","ros","v-rep"],"created_at":"2024-08-04T17:00:33.423Z","updated_at":"2024-11-21T08:31:27.237Z","avatar_url":"https://github.com/angelmtenor.png","language":"Python","funding_links":[],"categories":["实战"],"sub_categories":["ROS-RL-Kinetic"],"readme":"# RL-ROBOT\n\nÁngel Martínez-Tenor - 2016\n\n\u003cimg alt=\"Robot\" src=\"images/test_giraff.jpg\" width=\"300\"\u003e\n\nThis repository provides a Reinforcement Learning framework in Python from the Machine Perception and Intelligent Robotics research group [(MAPIR)](http://mapir.isa.uma.es).\n \nReference: *Towards a common implementation of reinforcement learning for multiple robotics tasks*. \u0026nbsp; [Arxiv preprint](https://arxiv.org/abs/1702.06329) \u0026nbsp;\u0026nbsp;\n[ScienceDirect](http://www.sciencedirect.com/science/article/pii/S0957417417307613) \n\n\n\u003cimg alt=\"Architecture\" src=\"images/architecture.jpg\" width=\"600\"\u003e\n\n\n## Getting Started\n\n**Setup**\n- Create a python environment and install the requirements. e.g. using conda:\n\n```\nconda create -n rlrobot python=3.10\nconda activate rlrobot\npip install -r requirements.txt\n# tkinter: sudo apt install python-tk \n```\n**Run**\n- Execute ```python run_custom_exp.py``` (content below)\n\n\n~~~\nimport exp\nimport rlrobot\n\nexp.ENVIRONMENT_TYPE = \"MODEL\"   # \"VREP\" for V-REP simulation\nexp.TASK_ID = \"wander_1k\"\nexp.FILE_MODEL = exp.TASK_ID + \"_model\"\n\nexp.ALGORITHM = \"TOSL\"\nexp.ACTION_STRATEGY = \"QBIASSR\"\n \nexp.N_REPETITIONS = 1\nexp.N_EPISODES = 1\nexp.N_STEPS = 60 * 60\n\nexp.DISPLAY_STEP = 500\n\nrlrobot.run()\n~~~\n- Full set of parameters available in `exp.py` \n\n- Tested on Ubuntu 14,16 ,18, 20 (64 bits)\n\n\n## V-REP settings: \nTested: V-REP PRO EDU V3.3.2 / V3.5.0\n\n![Scenarios](images/scenarios.jpg)\n\n\n1. Use default values of `remoteApiConnections.txt`\n    ~~~\n    portIndex1_port \t\t= 19997\n    portIndex1_debug \t\t= false\n    portIndex1_syncSimTrigger \t= true\n    ~~~\n\n2. Activate threaded rendering (recommended):\n    `system/usrset.txt -\u003e threadedRenderingDuringSimulation = 1` \n\nRecommended simulation settings for V-REP scenes:\n\n* Simulation step time: 50 ms  (default) \n* Real-Time Simulation: Enabled\n* Multiplication factor: 3.00 (required CPU \u003e= i3 3110m)\n\n **Execute V-REP** \n (`./vrep.sh on linux`). `File -\u003e Open Scene -\u003e \u003cRL-ROBOT path\u003e/vrep_scenes` \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangelmtenor%2FRL-ROBOT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fangelmtenor%2FRL-ROBOT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangelmtenor%2FRL-ROBOT/lists"}