• Stars
    star
    88
  • Rank 373,323 (Top 8 %)
  • Language
    Python
  • License
    MIT License
  • Created over 4 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Source Code for A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

More Repositories

1

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Python
5,285
star
2

portwarden

Create Encrypted Backups of Your Bitwarden Vault with Attachments
Go
568
star
3

ppo-implementation-details

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
Python
262
star
4

lm-human-preference-details

RLHF implementation details of OAI's 2019 codebase
Python
143
star
5

cleanba

CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL
Python
88
star
6

summarize_from_feedback_details

Python
81
star
7

PPO-Implementation-Deep-Dive

DEPRECATED - please visit https://github.com/vwxyzjn/ppo-implementation-details
Python
37
star
8

gym-microrts-paper

The source code for the gym-microrts paper.
Python
36
star
9

a2c_is_a_special_case_of_ppo

A2C is a special case of PPO!
Python
15
star
10

SC2AI

Integrated Tensorforce and OpenAI Gym to train SC II game agents.
Jupyter Notebook
13
star
11

jupyter_disqus

Add Disqus to your Jupyter notebook.
Python
13
star
12

gym-pysc2

Gym wrapper for pysc2
Python
8
star
13

envpool-cleanrl

Python
6
star
14

action-guidance

Python
6
star
15

ppo-atari-metrics

Python
4
star
16

vectorized-value-methods

[WIP] Vectorized architecture for value-based methods such as DQN and DDPG
Python
3
star
17

entity-ppo-demo

Python
2
star
18

CS583FinalProject

Python
1
star
19

Resume-master

TeX
1
star
20

minimal-adam-layer-norm-bug-repro

Python
1
star
21

embedding_projector

Python
1
star
22

RLControlSkipFrames

Python
1
star
23

launcha

Launcha is a simple Docker-based cloud job launcher.
Python
1
star
24

gym_minigrid

Python
1
star
25

CS618

Jupyter Notebook
1
star
26

validate-new-gym-mujoco-envs

Python
1
star
27

vuetify-parallax-starter2

JavaScript
1
star
28

envpool-xla-cleanrl

Python
1
star
29

cleanba-test

Python
1
star
30

envpool_bug

Python
1
star
31

Sentiment-Analysis-LSTM

Used neural network to classify movie reviews based on sentiment
Jupyter Notebook
1
star
32

aws-sagemaker-example

Jupyter Notebook
1
star
33

LP_optimization_python

Linear Programming for Optimal Scheduling by Using Gurobipy
TeX
1
star
34

CS583

Python
1
star
35

lm-human-preferences

Code for the paper Fine-Tuning Language Models from Human Preferences
Python
1
star