tile-coding

An environment to high-frequency trading agents under reinforcement learning

TF-Tile: an efficient sparse representation for real-valued data

In this all Projects dealing with reinforcement learning wil be uploaded

A tile coder in theano for Reinforcement Learning tasks

This repo constains the implementation of REINFORCE and REINFORCE-Baseline algorithm on Mountain car problem.

My programs during CS747 (Foundations of Intelligent and Learning Agents) Autumn 2021-22

Implementation of deep reinforcement learning

Code + frozen results for 'Forgotten Architectures #2 — CMAC on Modern Compute' — vulkgryph.com/research/nn-revival

Reinforcement learning lab work (Comillas ICAI, 2025): policy/value iteration, SARSA, Q-learning, tile coding and DQN agents

A reinforcement learning workbench that imports nothing. Every algorithm written out, every run reproducible from its seed, and three environments where the best possible policy under the stated reward is the wrong behaviour.

Constraint-aware reinforcement learning for 3-DOF spacecraft attitude control — PID vs standard RL vs reward-shaped CA-RL, compared on tracking error, actuator smoothness, control energy and disturbance rejection. Reproducible with one command.

Solving the Acrobot environment using Q-learning and Tile coding

Warehouse pick-up and delivery agents: SARSA(lambda) with tile coding, Q-learning, DQN

A repository covering a range of topics from multi-arm bandits to reinforcement learning algorithms. Check out different applications of bandits, MDPs and RL algorithms along with theoretical aspects.

A comparative study of 3 different Reinforcement Learning agents with 3 different state representations.

Lunar Lander RL Project