This repository has all the codes and sources of various RL algorithms that I have implemented.
-
Updated
Sep 22, 2020 - Python
#
tabular-rl
Here are 13 public repositories matching this topic...
A collection of deep and tabular reinforcement learning algorithms, including implementations of DQN, Dueling DQN, Q-learning, SARSA, n-step Tree Backup, and Monte Carlo.
-
Updated
Sep 6, 2024
Q-Learning Agent that Learns and Plays Alan Parr’s Traffic Lights Game
-
Updated
Jan 19, 2026 - Python
-
Updated
Nov 20, 2020 - Jupyter Notebook
Benchmarking 11 tabular RL methods on a 6×6 FrozenLake grid under deterministic and slippery dynamics.
-
Updated
Apr 12, 2026 - Python
Comparative study of Monte Carlo, SARSA & Q-Learning on custom MiniGrid environments. Phase-conditioned state representation, one-shot event-based reward shaping, Optuna hyperparameter search. TD methods: 100% success; MC: 61% on the hard env. RL course HW2, Reichman University.
python machine-learning reinforcement-learning deep-learning monte-carlo jupyter-notebook q-learning hyperparameter-optimization sarsa minigrid bayesian-optimization gymnasium reward-shaping temporal-difference optuna tabular-rl minigrid-environment
-
Updated
Jun 22, 2026 - Jupyter Notebook
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
mcts game-theory deepmind counterfactual-regret-minimization multi-agent-reinforcement-learning extensive-form-games strategy-games open-spiel tabular-rl two-player-games
-
Updated
Jul 23, 2025 - C++
Implementation of Q-Learning, SARSA, and Dyna Q to allow an agent to navigate the FrozenLake-v0 environment from OpenAI.
-
Updated
Dec 15, 2020 - Python
RL was cheaper. The heuristic was safer. Neither was correct. POLARIS stress-tests operational policies under chaos, demand spikes, and black swan events asking one question: which policy survives when everything goes wrong? Built with constrained RL, Bayesian modeling, CVaR risk metrics, and a human-in-the-loop governor.
python data-science reinforcement-learning simulation supply-chain q-learning stress-testing inventory-management operations-research human-in-the-loop chaos-engineering risk-modelling policy-optimization responsible-ai cvar duckdb tabular-rl decision-intelligence ai-governance bayesian-modeling
-
Updated
Mar 22, 2026 - Python
Q-Learning agent that learns to navigate a 4×12 cliff-edge grid using ε-greedy exploration and Bellman updates — trained from scratch with NumPy + Gymnasium in 63 lines of Python.
python reinforcement-learning numpy openai-gym q-learning epsilon-greedy gymnasium bellman-equation temporal-difference model-free-rl tabular-rl cliff-walking-problem
-
Updated
Jun 5, 2026 - Python
Matchbox-RL: A tangible reinforcement learning library for Python. Based on Donald Michie's 1961 MENACE algorithm using matchboxes and colored beads. Perfect for education and visualizing RL.
visualization python education machine-learning reinforcement-learning python-library tic-tac-toe q-learning artificial-intelligence game-ai matchbox menace ai-education tabular-rl
-
Updated
Dec 28, 2025 - Python
Optimize RAN parameters across 50 cells via tabular Q-Learning on cell-level KPI states (+61% vs random)
-
Updated
May 23, 2026 - Jupyter Notebook
强化学习中文学习笔记与可复现实验仓库，覆盖动态规划、表格方法、DQN、策略梯度、PPO、SAC 与安全强化学习专题。
python reinforcement-learning notes monte-carlo deep-reinforcement-learning q-learning dqn policy-gradient sarsa dynamic-programming experiments sac gymnasium actor-critic ppo safe-rl tabular-rl cmdp
-
Updated
Jun 13, 2026 - Python
Improve this page
Add a description, image, and links to the tabular-rl topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tabular-rl topic, visit your repo's landing page and select "manage topics."