Skip to content
Basic versions of agents from Spinning Up in Deep RL written in PyTorch
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
results
.gitignore
CONTRIBUTING.md
LICENSE.md
README.md
ddpg.py
dqn.py
env.py
hyperparams.py
models.py
ppo.py
requirements.txt
sac.py
td3.py
trpo.py
utils.py
vpg.py

README.md

spinning-up-basic

Basic versions of agents from Spinning Up in Deep RL written in PyTorch. Designed to run quickly on CPU on Pendulum-v0 from OpenAI Gym.

To see differences between algorithms, try running diff -y <file1> <file2>, e.g., diff -y ddpg.py td3.py.

For MPI versions of on-policy algorithms, see the mpi branch.

Algorithms

Results

Vanilla Policy Gradient/Advantage Actor-Critic

VPG

Trust Region Policy Gradient

TRPO

Proximal Policy Optimization

PPO

Deep Deterministic Policy Gradient

DDPG

Twin Delayed DDPG

TD3

Soft Actor-Critic

SAC

Deep Q-Network

DQN

Code Links

You can’t perform that action at this time.