kschweig

babyai

BabyAI platform. A testbed for training agents to understand and execute language commands.

BCQ

Author's PyTorch implementation of BCQ for continuous and discrete actions

CCC

Code for CCC

d4rl

A benchmark for offline reinforcement learning.

DDU

Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

DissectOfflineRL

Dissect Offline Reinforcement Learning, what do we need wrt. datasets and buffer strategies to succeed in this setting.

entropybaseduq

error-parity

Achieve error-rate fairness between societal groups for any score-based classifier.

GPT2-Volley

OfflineRL

Experiment for Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning

kschweig/OfflineRL

Experiment for Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning

kschweig/babyai

BabyAI platform. A testbed for training agents to understand and execute language commands.

kschweig/BCQ

Author's PyTorch implementation of BCQ for continuous and discrete actions

kschweig/CCC

Code for CCC

kschweig/d4rl

A benchmark for offline reinforcement learning.

kschweig/DDU

Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

kschweig/DissectOfflineRL

Dissect Offline Reinforcement Learning, what do we need wrt. datasets and buffer strategies to succeed in this setting.

kschweig/entropybaseduq

kschweig/error-parity

Achieve error-rate fairness between societal groups for any score-based classifier.

kschweig/GPT2-Volley

kschweig/gym-games

A gym version of various games for reinforcenment learning.

kschweig/hopfield-layers

Hopfield Networks is All You Need

kschweig/MinAtar

kschweig/offline-rl.github.io

kschweig/ProjectOfflineRL

Project work in the domain of offline RL

kschweig/python-zwoasi

Python binding for the ZWO ASI library. Control ZWO ASI cameras from python.

kschweig/shrinkbench-models

kschweig/SNNs

Tutorials and implementations for "Self-normalizing networks"

kschweig/spe2py

Loads Princeton Instruments LightField (SPE 3.0) files into a python environment.

kschweig/take_it_easy

Homebrew stochastic Reinforcement Learning environment to test various DRL algorithms on

kschweig/torch-sgld

SGLD and cSGLD as a PyTorch Optimizer

kschweig/understandingbdl