Alexander Nikulin

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

streaming-drl-jax. streaming deep reinforcement learning but 4x faster with jax!

link_pred_spark. similarity between graph nodes based on local information with PySpark

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

chess_minimax. minimax algorithm for chess with alpha-beta pruning

MHRW. metropolis-hastings random walk with PySpark

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

mst_clustering. implementation of agglomerative single linkage clustering with minimum spanning tree algorithm

Howuhh.github.io. HTML

tic_tac_toe_minimax. minimax algorithm implementation for tic tac toe

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

minerl_treechop_bc. MineRL TreeChop with Behavioural Cloning

autograd_but_smaller. Simple implementation of reverse-mode automatic differentiation on numpy arrays

halfcheetah_experts. expert policies for forward and backflip halfcheetah envs

Predators-and-Preys. Python

JaxMARL. Multi-Agent Reinforcement Learning with JAX

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

teaminfo. get info about your favorite team

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

cv. my cv, in case you're wondering

Ai.Hack. project from ai.hack

memory-maze. Evaluating long-term memory of reinforcement learning algorithms