Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

NGC-Learn: Computational Neuroscience and NeuroAI in Python

Agentic RL最详细入门

Curated papers, taxonomy, benchmarks, and decision guides for credit assignment in reasoning and agentic LLM reinforcement learning.

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)

Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurrent neural network models.

[AAAI 2023 Oral] Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition

[SSAC 2026] Better Prevent than Tackle: Valuing Defense in Soccer Based on Graph Neural Networks

A study of reinforcement learning algorithms for fed-batch bioprocessesing

Official codebase for the preprint: "Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO".

Awesome list of research publications and media on biologically-motivated learning algorithms.

Investigating methods for stable credit assignment for deep reinforcement learning

Various computational models for reinforcement learning

NGC-Learn: Predictive Coding and Neurobiologically-Motivated Learning in Python

We attempt to enhance multi-agent coordination in a tightly-coupled domain using auto-encoders.

Code accompanying "Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning"

Live proof of arXiv:2603.18859 — 0%→98% intermediate signal coverage

How far back can an RL agent trace credit for its success? SYNGrid is a configurable grid benchmark built to find out.

A persistent trust fabric for multi-agent AI: an irreversible, asymmetric matrix of gifts between agents where trust accumulates, credit is assigned, and deception is a measurable pathology. Grounded in the ontology of the gift (OWL/PROV-O).