proceduralia

motif

Intrinsic Motivation from Artificial Intelligence Feedback

MAGE

Learning Action-Value Gradients in Model-based Policy Optimization

cheatsheet-translation

Translation of VIP cheatsheets https://stanford.edu/~shervine/teaching/cs-229.html

high_replay_ratio_continuous_control

Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"

pytorch-conv2_1d

Pytorch implementation of (2+1)D spatiotemporal convolutions

pytorch-GAN-timeseries

GANs for time series generation in pytorch

pytorch-neural-enhance

Experiments on CNN-based image enhancement in pytorch

randomist

Code for Policy Optimization as Online Learning with Mediator Feedback

rl-algs-cheatsheet

RL poster-shaped cheatsheet

tgan-pytorch

A PyTorch implementation of Temporal Generative Adversarial Nets with Singular Value Clipping

proceduralia/pytorch-GAN-timeseries

GANs for time series generation in pytorch

proceduralia/pytorch-neural-enhance

Experiments on CNN-based image enhancement in pytorch

proceduralia/high_replay_ratio_continuous_control

Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"

proceduralia/pytorch-conv2_1d

Pytorch implementation of (2+1)D spatiotemporal convolutions

proceduralia/tgan-pytorch

A PyTorch implementation of Temporal Generative Adversarial Nets with Singular Value Clipping

proceduralia/rl-algs-cheatsheet

RL poster-shaped cheatsheet

proceduralia/randomist

Code for Policy Optimization as Online Learning with Mediator Feedback

proceduralia/cheatsheet-translation

Translation of VIP cheatsheets https://stanford.edu/~shervine/teaching/cs-229.html

proceduralia/brax

Massively parallel rigidbody physics simulation on accelerator hardware.

proceduralia/bsuite

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

proceduralia/experiment_buddy

proceduralia/proceduralia.github.io

proceduralia/TCN

Sequence modeling benchmarks and temporal convolutional networks

proceduralia/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs