Upside-Down Reinforcement Learning (⅂ꓤ) implementation in PyTorch. Based on the paper published by Jürgen Schmidhuber.

Implementation of Reinforcement Algorithms from scratch

Custom environment for OpenAI gym

The Asynchronous Advantage Actor Critic (A3C) algorithm is one of the newest algorithms to be developed under the field of Deep Reinforcement Learning Algorithms. This algorithm was developed by Google’s DeepMind which is the Artificial Intelligence division of Google. In this repository, I have my implementations of A3C on Cartpole game, Robot …

My attempt to beat dqn to the death by implementing as many RL algorithms on it possible

Implementation of certain crucial algorithms in the field of reinforcement learning.

Advantage Actor Critic with Temporal Difference on Cartpole-v0

In Cartpole Reinforcement Learning Environment, DQN, DDQN, and Dueling DQN methods are trained respectively.

a q-learning implementation of the cart pole environment in openai gym

Deep Reinforcement Learning containing 1) DQN 2) Double DQN 3) Dueling DQN 4) Noisy Net (Noisy DQN) 5) DQN with Prioritized Experience Replay 6) Noisy Double DQN with Prioritized Experience Replay 7) Noisy Dueling Double DQN with Prioritized Experience Replay

Implementation of RL algorithms in various environments

Open AI Cartpole environment gradient ascent

cartpole environment

DQN agent with e-greedy / softmax policy, experience replay and target network.

Exploring Active Federated Learning: Overcoming non-stationarity in distributed training via Target-Environment Probes, Active Weight aggregation, and Active Data fine-tuning.

Deep Q‑Network (DQN) implementation for solving CartPole‑v1 using PyTorch and Gymnasium. Includes training loop, replay buffer, target network updates, and evaluation with video rendering.

Reinforcement Learning Course Project