Package: ReinforcementLearning 1.0.5
ReinforcementLearning: Model-Free Reinforcement Learning
Performs model-free reinforcement learning in R. This implementation enables the learning of an optimal policy based on sample sequences consisting of states, actions and rewards. In addition, it supplies multiple predefined reinforcement learning algorithms, such as experience replay. Methodological details can be found in Sutton and Barto (1998) <ISBN:0262039249>.
Authors:
ReinforcementLearning_1.0.5.tar.gz
ReinforcementLearning_1.0.5.zip(r-4.5)ReinforcementLearning_1.0.5.zip(r-4.4)ReinforcementLearning_1.0.5.zip(r-4.3)
ReinforcementLearning_1.0.5.tgz(r-4.5-any)ReinforcementLearning_1.0.5.tgz(r-4.4-any)ReinforcementLearning_1.0.5.tgz(r-4.3-any)
ReinforcementLearning_1.0.5.tar.gz(r-4.5-noble)ReinforcementLearning_1.0.5.tar.gz(r-4.4-noble)
ReinforcementLearning_1.0.5.tgz(r-4.4-emscripten)ReinforcementLearning_1.0.5.tgz(r-4.3-emscripten)
ReinforcementLearning.pdf |ReinforcementLearning.html✨
ReinforcementLearning/json (API)
NEWS
| # Install 'ReinforcementLearning' in R: |
| install.packages('ReinforcementLearning', repos = c('https://nproellochs.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/nproellochs/reinforcementlearning/issues
- tictactoe - Game states of 100,000 randomly sampled Tic-Tac-Toe games.
experience-samplingreinforcement-learning
Last updated 5 years agofrom:b14091a532. Checks:1 OK, 7 NOTE. Indexed: yes.
| Target | Result | Latest binary |
|---|---|---|
| Doc / Vignettes | OK | Feb 08 2025 |
| R-4.5-win | NOTE | Feb 08 2025 |
| R-4.5-mac | NOTE | Feb 08 2025 |
| R-4.5-linux | NOTE | Feb 08 2025 |
| R-4.4-win | NOTE | Feb 08 2025 |
| R-4.4-mac | NOTE | Feb 08 2025 |
| R-4.3-win | NOTE | Feb 08 2025 |
| R-4.3-mac | NOTE | Feb 08 2025 |
Exports:computePolicyepsilonGreedyActionSelectionexperienceReplaygridworldEnvironmentpolicyrandomActionSelectionReinforcementLearningreplayExperiencesampleExperiencesampleGridSequenceselectEpsilonGreedyActionselectRandomActionstate
Dependencies:clicolorspacedata.tablefansifarverggplot2gluegtablehashisobandlabelinglatticelifecyclemagrittrMASSMatrixmgcvmunsellnlmepillarpkgconfigR6RColorBrewerrlangscalestibbleutf8vctrsviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Computes the reinforcement learning policy | computePolicy |
| Performs \varepsilon-greedy action selection | epsilonGreedyActionSelection |
| Performs experience replay | experienceReplay |
| Defines an environment for a gridworld example | gridworldEnvironment |
| Converts a name into an action selection function | lookupActionSelection |
| Loads reinforcement learning algorithm | lookupLearningRule |
| Computes the reinforcement learning policy | policy |
| Performs random action selection | randomActionSelection |
| Performs reinforcement learning | ReinforcementLearning rl |
| Performs experience replay | replayExperience |
| Sample state transitions from an environment function | sampleExperience |
| Sample grid sequence | sampleGridSequence |
| Performs \varepsilon-greedy action selection | selectEpsilonGreedyAction |
| Performs random action selection | selectRandomAction |
| Creates a state representation for arbitrary objects | state |
| Game states of 100,000 randomly sampled Tic-Tac-Toe games. | tictactoe |
