ahavenoname Goto Github PK

pytorch-a2c-ppo-acktr

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

pytorch-rl

Deep Reinforcement Learning with pytorch & visdom

q-learning-delusion

A counterexample for Q-Learning, discussed in "Non-delusional Q-learning and value-iteration."

quant-projects

Implementations of Leading Algorithms in Quantitative Finance

rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

random-network-distillation

Code for the paper "Exploration by Random Network Distillation"

rlkit

Collection of reinforcement learning algorithms

rllabplusplus

rnd

Exploration by Random Network Distillation

simionzoo

A workbench for online model-free Reinforcement Learning on continuous control problems

sptm

[ICLR 2018] Tensorflow/Keras code for Semi-parametric Topological Memory for Navigation

synthetic-computer-vision

A list of synthetic dataset and tools for computer vision

taxi

Hierarchical Online Planning and Reinforcement Learning on Taxi

temporal_abstraction

Option Critic with subgoal discovery by spectral decomposition of the Successor Features Matrix or clustering in Successor features space.

tscl

Teacher-Student Curriculum Learning code

ucrl

uncertaintynn

Implementation and evaluation of different approaches to get uncertainty in neural networks

visual_foresight

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control

worldmodels.github.io

World Models

worldmodelsexperiments

World Models Experiments