PyTorch implementation of various reinforcement learning algorithms
-
Updated
Feb 22, 2018 - Python
PyTorch implementation of various reinforcement learning algorithms
Prioritized Experience Replay for Reinforcement Learning
This project aims apply Dueling Deep Q Learning with Prioritized experience to play game 2048
A novel DDPG method with prioritized experience replay (IEEE SMC 2017)
A RL agent that learns to play doom's deadly corridor based on DDQN and PER.
PGuNN - Playing Games using Neural Networks
(Prioritized experience replay, random uniform replay) with tabular-Q for blind cliffwalk problem introduced as a motivating example in the publication Schaul et al., 2015
Applying the DQN-Agent from keras-rl to Starcraft 2 Learning Environment and modding it to to use the Rainbow-DQN algorithms.
Reinforcement learning of point to point reaching
Repository for codes of 'Deep Reinforcement Learning'
DQN, DDQN - using experience replay or prioritized experience replay
Using N-step dueling DDQN with PER for playing Pacman game
Prioritized Experience Replay (PER) implementation in PyTorch
A merge between OpenAI Baselines and Stable Baselines with increased focus on HER+DDPG and ease of use. Simply run the bash script to get started!
reinforcement learning framework with pytorch
Another Addition to the Pile of Deep Q Learning, Double DQN, PER, Dueling DQN Implementations
Exploring different buffer sampling techniques to improve Hindisght Experience Replay on continuous control robotic application tasks. Continous action spaces & sparse rewards.
Implementation and evaluation of the RL algorithm Rainbow to learn to play Atari games.
Add a description, image, and links to the prioritized-experience-replay topic page so that developers can more easily learn about it.
To associate your repository with the prioritized-experience-replay topic, visit your repo's landing page and select "manage topics."