# Rethinking Value Function Learning for Generalization in Reinforcement Learning

arXiv: https://arxiv.org/abs/2210.09960 · HTML: https://mlsanity.com/paper/2210.09960/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [DeepMDP: Learning Continuous Latent Space Models for Representation Learning](https://mlsanity.com/paper/1906.02736/) (2019)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [Phasic Policy Gradient](https://mlsanity.com/paper/2009.04416/) (2020)
- [Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.05265/) (2021)
- [Generalization and Regularization in DQN](https://mlsanity.com/paper/1810.00123/) (2018)
- [Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck](https://mlsanity.com/paper/1910.12911/) (2019)
- [Observational Overfitting in Reinforcement Learning](https://mlsanity.com/paper/1912.02975/) (2019)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [Deep Reinforcement and InfoMax Learning](https://mlsanity.com/paper/2006.07217/) (2020)
- [BackPACK: Packing more into backprop](https://mlsanity.com/paper/1912.10985/) (2019)
- [The Value-Improvement Path: Towards Better Representations for Reinforcement Learning](https://mlsanity.com/paper/2006.02243/) (2020)
- [Stiffness: A New Perspective on Generalization in Neural Networks](https://mlsanity.com/paper/1901.09491/) (2019)

## Built on by (most cited first, 8 of 8)

- [Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning](https://mlsanity.com/paper/2503.06343/) (2025)
- [Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning](https://mlsanity.com/paper/2307.03486/) (2023)
- [Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs](https://mlsanity.com/paper/2410.03565/) (2024)
- [Representation Convergence: Mutual Distillation is Secretly a Form of Regularization](https://mlsanity.com/paper/2501.02481/) (2025)
- [Adaptive Data Exploitation in Deep Reinforcement Learning](https://mlsanity.com/paper/2501.12620/) (2025)
- [Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning](https://mlsanity.com/paper/2502.08336/) (2025)
- [Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2406.08069/) (2024)
- [Zero-Shot Action Generalization with Limited Observations](https://mlsanity.com/paper/2503.08867/) (2025)

## Abstract (arXiv)

Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks are separately optimized using a disjoint network architecture to avoid interference and obtain a more accurate value function. We identify that a value network in the multi-environment setting is more challenging to optimize and prone to memorizing the training data than in the conventional single-environment setting. In addition, we find that appropriate regularization on the value network is necessary to improve both training and test performance. To this end, we propose Delayed-Critic Policy Gradient (DCPG), a policy gradient algorithm that implicitly penalizes value estimates by optimizing the value network less frequently with more training data than the policy network. This can be implemented using a single unified network architecture. Furthermore, we introduce a simple self-supervised task that learns the forward and inverse dynamics of environments using a single discriminator, which can be jointly optimized with the value network. Our proposed algorithms significantly improve observational generalization performance and sample efficiency on the Procgen Benchmark.