{ "_id": "6a1c05621d7bb097a0a2ac39", "Package": "ReinforcementLearning", "Type": "Package", "Title": "Model-Free Reinforcement Learning", "Version": "1.0.5", "Date": "2020-03-02", "Authors@R": "c(person(\"Nicolas\", \"Proellochs\", email=\"nicolas.proellochs@wi.jlug.de\",\nrole=c(\"aut\", \"cre\")),\nperson(\"Stefan\", \"Feuerriegel\", email=\"sfeuerriegel@ethz.ch\",\nrole=c(\"aut\")))", "Maintainer": "Nicolas Proellochs ", "Description": "Performs model-free reinforcement learning in R. This\nimplementation enables the learning of an optimal policy based\non sample sequences consisting of states, actions and rewards.\nIn addition, it supplies multiple predefined reinforcement\nlearning algorithms, such as experience replay. Methodological\ndetails can be found in Sutton and Barto (1998)\n.", "License": "MIT + file LICENSE", "LazyData": "TRUE", "Encoding": "UTF-8", "RoxygenNote": "6.1.1", "VignetteBuilder": "knitr", "Repository": "https://nproellochs.r-universe.dev", "Date/Publication": "2020-03-02 01:29:53 UTC", "RemoteUrl": "https://github.com/nproellochs/reinforcementlearning", "RemoteRef": "HEAD", "RemoteSha": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-31 09:50:39 UTC", "User": "root" }, "Author": "Nicolas Proellochs [aut, cre],\nStefan Feuerriegel [aut]", "MD5sum": "fae3b4f29b03a270fccb0de1f5943bc1", "_user": "nproellochs", "_type": "src", "_file": "ReinforcementLearning_1.0.5.tar.gz", "_fileid": "fa841cd6d62408095401d88453f380aaa5e985af4b2ec7545c19df5ffb6595c3", "_filesize": 1094288, "_sha256": "fa841cd6d62408095401d88453f380aaa5e985af4b2ec7545c19df5ffb6595c3", "_created": "2026-05-31T09:50:39.000Z", "_published": "2026-05-31T09:54:42.343Z", "_distro": "noble", "_jobs": [ { "job": 78716564461, "time": 125, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7315746321" }, { "job": 78716564464, "time": 121, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7315745960" }, { "job": 78716564481, "time": 214, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "NOTE", "artifact": "7315751684" }, { "job": 78716564467, "time": 194, "config": "macos-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7315749601" }, { "job": 78716408263, "time": 172, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7315734117" }, { "job": 78716564476, "time": 104, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7315744156" }, { "job": 78716564486, "time": 85, "config": "windows-devel", "r": "4.7.0", "check": "NOTE", "artifact": "7315742320" }, { "job": 78716564470, "time": 83, "config": "windows-oldrel", "r": "4.5.3", "check": "NOTE", "artifact": "7315742156" }, { "job": 78716564480, "time": 80, "config": "windows-release", "r": "4.6.0", "check": "NOTE", "artifact": "7315741810" } ], "_buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/nproellochs/reinforcementlearning", "_commit": { "id": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "author": "nproellochs ", "committer": "nproellochs ", "message": "Updated DESCRIPTION\n", "time": 1583112593 }, "_maintainer": { "name": "Nicolas Proellochs", "email": "nicolas.proellochs@wi.jlug.de", "login": "nproellochs", "description": "", "uuid": 16661066 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.2.0", "role": "Depends" }, { "package": "ggplot2", "role": "Imports" }, { "package": "hash", "version": ">= 2.0", "role": "Imports" }, { "package": "data.table", "role": "Imports" }, { "package": "testthat", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "nproellochs", "_selfowned": true, "_usedby": 1, "_updates": [], "_tags": [], "_topics": [ "experience-sampling", "reinforcement-learning" ], "_stars": 69, "_contributors": [ { "user": "nproellochs", "count": 60, "uuid": 16661066 } ], "_userbio": { "uuid": 16661066, "type": "user", "name": "Nicolas Pröllochs" }, "_downloads": { "count": 257, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/ReinforcementLearning" }, "_devurl": "https://github.com/nproellochs/reinforcementlearning", "_searchresults": 213, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/ReinforcementLearning.html", "manual.pdf" ], "_homeurl": "https://github.com/nproellochs/reinforcementlearning", "_realowner": "nproellochs", "_cranurl": true, "_releases": [ { "version": "1.0.0", "date": "2017-04-18" }, { "version": "1.0.1", "date": "2017-06-19" }, { "version": "1.0.2", "date": "2018-04-08" }, { "version": "1.0.3", "date": "2019-04-22" }, { "version": "1.0.4", "date": "2019-05-25" }, { "version": "1.0.5", "date": "2020-03-02" } ], "_exports": [ "computePolicy", "epsilonGreedyActionSelection", "experienceReplay", "gridworldEnvironment", "policy", "randomActionSelection", "ReinforcementLearning", "replayExperience", "sampleExperience", "sampleGridSequence", "selectEpsilonGreedyAction", "selectRandomAction", "state" ], "_datasets": [ { "name": "tictactoe", "title": "Game states of 100,000 randomly sampled Tic-Tac-Toe games.", "object": "tictactoe", "class": [ "data.frame" ], "fields": [ "State", "Action", "NextState", "Reward" ], "rows": 406541, "table": true, "tojson": true } ], "_help": [ { "page": "computePolicy", "title": "Computes the reinforcement learning policy", "topics": [ "computePolicy" ] }, { "page": "epsilonGreedyActionSelection", "title": "Performs \\varepsilon-greedy action selection", "topics": [ "epsilonGreedyActionSelection" ] }, { "page": "experienceReplay", "title": "Performs experience replay", "topics": [ "experienceReplay" ] }, { "page": "gridworldEnvironment", "title": "Defines an environment for a gridworld example", "topics": [ "gridworldEnvironment" ] }, { "page": "lookupActionSelection", "title": "Converts a name into an action selection function", "topics": [ "lookupActionSelection" ] }, { "page": "lookupLearningRule", "title": "Loads reinforcement learning algorithm", "topics": [ "lookupLearningRule" ] }, { "page": "policy", "title": "Computes the reinforcement learning policy", "topics": [ "policy" ] }, { "page": "randomActionSelection", "title": "Performs random action selection", "topics": [ "randomActionSelection" ] }, { "page": "ReinforcementLearning", "title": "Performs reinforcement learning", "topics": [ "ReinforcementLearning", "rl" ] }, { "page": "replayExperience", "title": "Performs experience replay", "topics": [ "replayExperience" ] }, { "page": "sampleExperience", "title": "Sample state transitions from an environment function", "topics": [ "sampleExperience" ] }, { "page": "sampleGridSequence", "title": "Sample grid sequence", "topics": [ "sampleGridSequence" ] }, { "page": "selectEpsilonGreedyAction", "title": "Performs \\varepsilon-greedy action selection", "topics": [ "selectEpsilonGreedyAction" ] }, { "page": "selectRandomAction", "title": "Performs random action selection", "topics": [ "selectRandomAction" ] }, { "page": "state", "title": "Creates a state representation for arbitrary objects", "topics": [ "state" ] }, { "page": "tictactoe", "title": "Game states of 100,000 randomly sampled Tic-Tac-Toe games.", "topics": [ "tictactoe" ] } ], "_readme": "https://github.com/nproellochs/reinforcementlearning/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "data.table", "farver", "ggplot2", "glue", "gtable", "hash", "isoband", "labeling", "lifecycle", "R6", "RColorBrewer", "rlang", "S7", "scales", "vctrs", "viridisLite", "withr" ], "_vignettes": [ { "source": "ReinforcementLearning.Rmd", "filename": "ReinforcementLearning.html", "title": "Reinforcement Learning in R", "author": "Nicolas Pröllochs", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "The reinforcement learning problem", "Policy learning", "Experience replay", "Setup of the ReinforcementLearning package", "Installation", "Package loading", "Usage", "Data preparation", "Learning from pre-defined observations", "Dynamic learning from an interactive environment function", "Learning phase", "General setup", "Parameter configuration", "Diagnostics", "Working example 1: Gridworld", "Problem definition", "Defining an environment function", "Learning an optimal policy", "Evaluating policy learning", "Applying a policy to unseen data", "Updating an existing policy", "Working example 2: Tic-Tac-Toe", "Notes on performance", "License" ], "created": "2017-03-29 17:57:49", "modified": "2019-05-24 23:55:21", "commits": 11 } ], "_score": 7.343319953231674, "_indexed": true, "_nocasepkg": "reinforcementlearning", "_universes": [ "nproellochs" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.5", "date": "2026-05-31T09:52:39.000Z", "distro": "noble", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "92b875b71859ee57028637a02bf6c17773695cd0e29c6fab172de356088e9272", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.6.0", "os": "linux", "version": "1.0.5", "date": "2026-05-31T09:52:37.000Z", "distro": "noble", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "5d2f7fe5c0e09bb3d4e0657aa404816da0ed72fa3e9b285d6a64e9589a9a6a69", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.5.3", "os": "mac", "version": "1.0.5", "date": "2026-05-31T09:53:27.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "e3f3220382ed1a584756c76b175e3d91ed8643e0fee4bba5d0304a0b7d50f8a4", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.6.0", "os": "mac", "version": "1.0.5", "date": "2026-05-31T09:53:06.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "900446ca828d951da9509f621dbc5a12a4b876beb908f916354ad804fa0fc152", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.5", "date": "2026-05-31T09:52:37.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "07e69b0b602484164f079c79405b42b05b0586875023f7101b9e85f06de5ab91", "status": "success", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.7.0", "os": "win", "version": "1.0.5", "date": "2026-05-31T09:51:54.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "0f37c402e6e67b1dba64e397c678d70f018890744757dc429d8af1b1f095cc45", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.5.3", "os": "win", "version": "1.0.5", "date": "2026-05-31T09:51:53.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "f76faf3252efec1b39566c3a1649016b61df2916c5008c4231c870fb01be2bc1", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" }, { "r": "4.6.0", "os": "win", "version": "1.0.5", "date": "2026-05-31T09:51:48.000Z", "commit": "b14091a5320dcaf7c10766c0968eb997fe068b6b", "fileid": "dedf76bfd7d04643a97b73bef1f54bebcad53dd6baa8bba30f812c2909aba8c8", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/nproellochs/actions/runs/26709298434" } ] }