Howuhh

faster-trajectory-transformer

Implementation of Trajectory Transformer with attention caching and batched beam search

prioritized_experience_replay

Prioritized Experience Replay implementation with proportional prioritization

sac-n-jax

Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch

evolution_strategies_openai

implementation of "Evolution Strategies as a Scalable Alternative to Reinforcement Learning" OpenAI paper

link_pred_spark

similarity between graph nodes based on local information with PySpark

chess_minimax

minimax algorithm for chess with alpha-beta pruning

average_reward_ppo

Implementation of "Average-Reward Reinforcement Learning with Trust Region Methods" paper.

MHRW

metropolis-hastings random walk with PySpark

cic_gym

Adaptation of original "Contrastive Intrinsic Control for Unsupervised Skill Discovery" implementation to OpenAI Gym

Howuhh.github.io

halfcheetah_experts

expert policies for forward and backflip halfcheetah envs

Predators-and-Preys

JaxMARL

Multi-Agent Reinforcement Learning with JAX

pgx

🎲 Vectorized RL game environments written in JAX with end-to-end AlphaZero examples

cic

CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

d4rl

A benchmark for offline reinforcement learning.

dul_2021

hse_bayesian_ml

hse_recsys

hse recommender systems course

hse_reinforcement_learning

HSE Reinforcement Learning course

linear-transformer-experiments

Experiments using fast linear transformer

link_pred

link prediction in social network based on node neighborhoods

memory-maze

Evaluating long-term memory of reinforcement learning algorithms

Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

tomita-gym

[TBD] Environments based on Tomita Grammars

TTS_HW

vector-quantize-pytorch

Vector Quantization, in Pytorch