{"id":23253263,"url":"https://github.com/sharathraparthy/nearest_sequence_memory","last_synced_at":"2025-04-06T03:15:28.984Z","repository":{"id":71133356,"uuid":"155598110","full_name":"SharathRaparthy/nearest_sequence_memory","owner":"SharathRaparthy","description":"Reimplementation of the paper \"Instance-Based  State Identification for Reinforcement Learning \"","archived":false,"fork":false,"pushed_at":"2018-11-08T10:28:55.000Z","size":44,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-12T09:28:28.217Z","etag":null,"topics":["algorithm","matlab","reinforcement-learning","reinforcement-learning-agent"],"latest_commit_sha":null,"homepage":"","language":"Matlab","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/SharathRaparthy.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-10-31T17:31:02.000Z","updated_at":"2021-04-29T15:33:14.000Z","dependencies_parsed_at":"2023-02-26T03:00:33.829Z","dependency_job_id":null,"html_url":"https://github.com/SharathRaparthy/nearest_sequence_memory","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SharathRaparthy%2Fnearest_sequence_memory","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SharathRaparthy%2Fnearest_sequence_memory/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SharathRaparthy%2Fnearest_sequence_memory/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SharathRaparthy%2Fnearest_sequence_memory/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SharathRaparthy","download_url":"https://codeload.github.com/SharathRaparthy/nearest_sequence_memory/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247427012,"owners_count":20937214,"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":["algorithm","matlab","reinforcement-learning","reinforcement-learning-agent"],"created_at":"2024-12-19T10:29:50.003Z","updated_at":"2025-04-06T03:15:28.959Z","avatar_url":"https://github.com/SharathRaparthy.png","language":"Matlab","readme":"# Nearest Sequence Memory for Hidden State Idenification\n\nThis repository is the *reimplementation* of the paper \"[Instance-Based State Identification for Reinforcement Learning](https://papers.nips.cc/paper/932-instance-based-state-identification-for-reinforcement-learning.pdf)\" by [R.Andrew McCallum](https://people.cs.umass.edu/~mccallum/)\n\nNSM is an instance-based algorithm for solving partially observable Markov decision problems (POMDPs). Here NSM algorithm is applies to a partially obsevable version of McCallum's grid-world presented in figure below.\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"460\" height=\"300\" src=\"https://raw.githubusercontent.com/SharathRaparthy/semantic_segmentation/master/discrete_world.png\"\u003e\n\u003c/p\u003e\n\n### Prerequisites\n```\nMatlab 2015b (or later version)\nUbuntu 14.04 (or later version)/Windows\n```\n\n\n### Getting Started\nAfter successful installation of matlab, clone this repository by using the following command\n\n```\ngit clone https://github.com/SharathRaparthy/nearest_sequence_memory.git\n```\nOpen your matlab and execute *rndTrial.m* script with the following MATLAB command:\n\n```\nplot(rndTrial(1000));\n```\nThe result should like similar to figure below, but it should not be exactly the same.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"460\" height=\"300\" src=\"https://raw.githubusercontent.com/SharathRaparthy/nearest_sequence_memory/master/rndTrial.png\"\u003e\n\u003c/p\u003e\n\n\nNow run the NSMTrial function and plot the individual number of steps taken for 1000\nepisodes using the MATLAB command:\n```\nplot(NSMTrial(1000));\n```\nThe result should like similar to Figure shown below but it should not be exactly the same.\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"460\" height=\"300\" src=\"https://raw.githubusercontent.com/SharathRaparthy/semantic_segmentation/master/NSMplot.png\"\u003e\n\u003c/p\u003e\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharathraparthy%2Fnearest_sequence_memory","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsharathraparthy%2Fnearest_sequence_memory","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharathraparthy%2Fnearest_sequence_memory/lists"}