# CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration

arXiv: https://arxiv.org/abs/2105.03923 · HTML: https://mlsanity.com/paper/2105.03923/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 25 of 25)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Safe and Efficient Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1606.02647/) (2016)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout](https://mlsanity.com/paper/2010.06808/) (2020)
- [Bridging the Gap Between Value and Policy Based Reinforcement Learning](https://mlsanity.com/paper/1702.08892/) (2017)
- [Phasic Policy Gradient](https://mlsanity.com/paper/2009.04416/) (2020)
- [RotoGrad: Gradient Homogenization in Multitask Learning](https://mlsanity.com/paper/2103.02631/) (2021)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [Off-Policy Actor-Critic with Shared Experience Replay](https://mlsanity.com/paper/1909.11583/) (2019)
- [An operator view of policy gradient methods](https://mlsanity.com/paper/2006.11266/) (2020)
- [Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field](https://mlsanity.com/paper/1908.04683/) (2019)

## Built on by (most cited first, 1 of 1)

- [Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards](https://mlsanity.com/paper/2510.20867/) (2025)

## Abstract (arXiv)

We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI). While GPI is typically an interplay between policy evaluation and policy improvement, most conventional model-free methods assume the independence of the granularity and other details of the GPI steps, despite of the inherent connections between them. In this paper, we present a method that regularizes the inconsistency between policy evaluation and policy improvement, leading to a conflict averse GPI solution with reduced functional approximation error. To this end, we formulate a novel learning paradigm where taking the policy evaluation step is equivalent to some compensation of performing policy improvement, and thus effectively alleviates the gradient conflict between the two GPI steps. We also show that the form of our proposed solution is equivalent to performing entropy-regularized policy improvement and therefore prevents the policy from being trapped into suboptimal solutions. We conduct extensive experiments to evaluate our method on the Arcade Learning Environment (ALE). Empirical results show that our method outperforms several strong baselines in major evaluation domains.