Howuhh

xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

chess_minimax

minimax algorithm for chess with alpha-beta pruning

cs_algorithms

code for courses on algorithms and data structures from CSC & leetcode & CSES problem set

evolution_strategies_openai

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

faster-trajectory-transformer

Implementation of Trajectory Transformer with attention caching and batched beam search

link_pred_spark

similarity between graph nodes based on local information with PySpark

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

CORL

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

sac-rnd

Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023

Howuhh/faster-trajectory-transformer

Implementation of Trajectory Transformer with attention caching and batched beam search

Howuhh/prioritized_experience_replay

Prioritized Experience Replay implementation with proportional prioritization

Howuhh/sac-n-jax

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

Howuhh/evolution_strategies_openai

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

Howuhh/link_pred_spark

similarity between graph nodes based on local information with PySpark

Howuhh/chess_minimax

minimax algorithm for chess with alpha-beta pruning

Howuhh/average_reward_ppo

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

Howuhh/MHRW

metropolis-hastings random walk with PySpark

Howuhh/cic_gym

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

Howuhh/Howuhh.github.io

Howuhh/halfcheetah_experts

expert policies for forward and backflip halfcheetah envs

Howuhh/Predators-and-Preys

Howuhh/JaxMARL

Multi-Agent Reinforcement Learning with JAX

Howuhh/pgx

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

Howuhh/cic

CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery

Howuhh/cleanrl

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

Howuhh/d4rl

A benchmark for offline reinforcement learning.

Howuhh/dul_2021

Howuhh/hse_bayesian_ml

Howuhh/hse_recsys

hse recommender systems course

Howuhh/hse_reinforcement_learning

HSE Reinforcement Learning course

Howuhh/linear-transformer-experiments

Experiments using fast linear transformer

Howuhh/link_pred

link prediction in social network based on node neighborhoods

Howuhh/memory-maze

Evaluating long-term memory of reinforcement learning algorithms

Howuhh/Minari

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

Howuhh/mujoco-py

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

Howuhh/robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Howuhh/tomita-gym

[TBD] Environments based on Tomita Grammars

Howuhh/TTS_HW

Howuhh/vector-quantize-pytorch

Vector Quantization, in Pytorch