search

BY571 / Munchausen-RL

PyTorch implementation of the Munchausen Reinforcement Learning Algorithms M-DQN and M-IQN
41 stars 1 forks source link
deep-q-learning deep-reinforcement-learning maximum-entropy munchausen-reinforcement-learning reinforcement-learning reinforcement-learning-algorithms temporal-differencing-learning

readme

Munchause-RL

PyTorch implementation of the M-DQN algorithm based on the paper Munchause Reinforcement Learning.

For a short introduction check out the Medium Article!

Implementations

Discrete Action Space:

Continuous Action Space:

Changes to the Paper

Compared to the original algorithm I did some changes:

  1. Instead of doing a hard update every 8000 frames I implemented a soft-update. By personal experience this worked better.

Results

Comparison runs between M-DQN and DQN for the CartPole-v0 environment and LunarLander-v2.

altext

altext

Comparison of IQN and M-IQN for LunarLander-v2

altext

Comparison IQN and M-IQN for Breakout

altext