tpbarron/pytorch-ppo

Stars
39
Rank 690,037 (Top 14 %)
Language
Python
License
MIT License
Created about 7 years ago
Updated almost 7 years ago

tpbarron/pytorch-ppo

tpbarron

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

Proximal Policy Optimization in PyTorch

rlflow

A TensorFlow-based framework for learning about and experimenting with reinforcement learning algorithms

pytorch-a2c

Simple change of a3c to a2c

gym-baxter

Open AI gym environment for the Baxter robot

mathjax_mathspeak

MathJax with MathSpeak for each expression

jetsonhardware

Library interface for sensor access on the NVidia Jetson TK1 via I2C

iprims

A basic implementation of the Interaction Primitives framework for human robot collaboration

cuda_ann

A neural network implementation in CUDA (undergraduate capstone project)

torch_nlp_autoencoder

Torch autoencoder built for NLP experimentation

infomax_rec_system

Recommendations for maximum information gain

gym-x

Exploration tasks for Gym

CaffeAutoencoderViz

A tool to visualize the learned features of stacked autoencoders trained on natural language data with Caffe

imle

Information Maximizing Latent Exploration

MathMLParser

MathML parser to produce valid MathSpeak text

rl-adaptive-sampling

policy_model_equiv

Updating policy with model gradient

ngrammer_pos

NLP using n-grams and part of speech

mentee_networks

Mentee networks implementation in Keras and TensorFlow

swapr

Craigslist-like website for Colorado College

vehicle_optimization

Vehicle simulator to test algorithms for traffic optimization.

minecraft_dqn_interface

An interface to communicate between caffe dqn and python minecraft

adacurv

Adaptive curvature for stochastic optimization