# Policy Invariance under Reward Transformations for General-Sum Stochastic Games

arXiv: https://arxiv.org/abs/1401.3907 · HTML: https://mlsanity.com/paper/1401.3907/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2014.

## Built on by (most cited first, 6 of 6)

- [Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2201.04612/) (2022)
- [Shaping Advice in Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2103.15941/) (2021)
- [MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue](https://mlsanity.com/paper/2603.06194/) (2026)
- [Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2412.14779/) (2024)
- [Shaping Advice in Deep Reinforcement Learning](https://mlsanity.com/paper/2202.09489/) (2022)
- [ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.23562/) (2026)

## Abstract (arXiv)

We extend the potential-based shaping method from Markov decision processes to multi-player general-sum stochastic games. We prove that the Nash equilibria in a stochastic game remains unchanged after potential-based shaping is applied to the environment. The property of policy invariance provides a possible way of speeding convergence when learning to play a stochastic game.