Skip to content

LoheshM/Reinforcement-Learning-

View on GitHub ↗Related repositories →

Implemented a Multi-Armed Bandit solution for article recommendation using Epsilon-Greedy and Thompson Sampling strategies, alongside a pathfinding agent for a 100x100 grid using MDP, Monte Carlo, and Value Iteration. Enhanced with Boltzmann exploration, epsilon decay, model saving/loading, and episode length constraints for improved efficiency.

active 2024-11-06 → 2024-11-06 (UTC)

Complete coverage27,459 / 27,459 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-10-02 (UTC)
Events
4
Pushes
3
Pull requests
0
Issues
0
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 1 days from 2024-11-06 to 2024-11-06. Pushes: 3 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
LoheshM3300

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.