Rl Environment Python Packages

nemo-gym

Evaluate and improve models and agents using environments

openenv

Open-source environments for reinforcement learning. No need for MuJoCo!

moonfish

~2000 Elo Python Chess Engine that implements: Negamax, PeSTO’s Evaluation, Null Move, Quiescence Search, Lazy SMP.

carl-studio

CARL (Coherence-Aware Reinforcement Learning) — information-theoretic reward signals for LLM training via token-level probability distributions

xenoverse

Benchmarking general decision-making with open & random worlds

forest-gen

Forest generation module utilizing STRIPE-kit

carl-core

Coherence math primitives for CARL (Coherence-Aware Reinforcement Learning)

floxs

Multi-agent RL flock and swarm environments implemented in JAX