anyboby Goto Github PK

a2c_sonic

a3c_cartpole

a3c_cont_car_racing

Python3 Remake of Jang et al. - Reinforcement Car Racing with A3C

a3c_continuous

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

car_racing

openai gym car_racing with a3c

carlarl

DDPG and Birds-Eye-View Generation for CARLA

classification_bandits

This is a set of bandit problems based on common classification datasets. Insipired by the bsuite mnist bandit.

constrained-model-based-policy-optimization

Code for a model-based version of Constrained Policy Optimization

constrainedmbpo

Constrained Version of Model-Based Policy Optimization (e.g. CPO as model-free optimizer)

cpo

CPO with few additional features s.a. adaptive parameter noise

deepreinforcementlearning_playground

distributionalregression

dqn_doom

l2l_humanbrainproject

master-board

Hardware and Firmware of the Solo Quadruped Master Board

mbpo

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

mujoco_safety_gym

probabilisticensemble

requirements_dataset

A dataset of short texts from various german requirements specifications.

rnn_langmodel

RNN Assigment for Lecture Deep Learning

safety-gym

Tools for accelerating safe exploration research.

safety-starter-agents

Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.

vizdoomgym

OpenAI Gym wrapper for ViZDoom enviroments, including additional sparse scenarios