Repositories
coadapt-marl
krm9c/coadapt-marl
Decentralized multi-agent RL harness under partial observability (JAX). Per-agent solvers: REINFORCE, PPO, GRPO, TRPO, recurrent.
Docs & code →SWARM
swarm-workflows
Scientific Workflow Management for Distributed Research Infrastructure
View on GitHub →Flow-Bench
pegasus-isi/FlowBench
Dataset and benchmarks for computational workflow anomaly detection
View on GitHub →Meta-Continual-Learning
krm9c/Meta-Continual-Learning
Meta-learning approaches for continual learning
View on GitHub →View more projects and contributions on GitHub