No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

1 code implementation • 1 May 2024 • Skander Moalla, Andrea Miele, Razvan Pascanu, Caglar Gulcehre

We draw connections between representation collapse, performance collapse, and trust region issues in PPO, and present Proximal Feature Optimization (PFO), a novel auxiliary loss, that along with other interventions shows that regularizing the representation dynamics improves the performance of PPO agents.

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

1 code implementation • NeurIPS 2023 • Benjamin Ellis, Jonathan Cook, Skander Moalla, Mikayel Samvelyan, Mingfei Sun, Anuj Mahajan, Jakob N. Foerster, Shimon Whiteson

In this work, we conduct new analysis demonstrating that SMAC lacks the stochasticity and partial observability to require complex *closed-loop* policies.

reinforcement-learning SMAC+ +1