masonn808 Goto Github PK

activation-function-plots

activation-functions

ai-poker-agent

Starter code for CompSci 683 project

ai-safety-gridworlds

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

algorithms

bayesian

cart-pole

cmpt-220l-903-21s

compilers

covid-19_visualization

cpo-toy-av

Constrained Policy Optimization

data-capping

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

downward

The Fast Downward domain-independent classical planning system

empirical-methods

ethically-compliant-rl

ethically-compliant-rl-racing

An OpenAI Gym environment for multi-agent car racing based on Gym's original car racing environment.

fsrl

🚀 A fast safe reinforcement learning library in PyTorch

gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

highwayenv

A minimalist environment for decision-making in autonomous driving

induced-h-saturated-graphs

llms-planning

An extensible benchmark for evaluating large language models on planning

mamba-hf

Implementation of the Mamba SSM with hf_integration.

masonzjavaneural

metaprogramming-for-contract-algorithms

minigrid

Simple and easily configurable grid world environments for reinforcement learning

mle_research

os808

Operating Systems Course

personal_website

Mason's Personal Website

personal_website_2.0

Mason Nakamura's personal website