# Adversarially Trained Actor Critic for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2202.02446 · HTML: https://mlsanity.com/paper/2202.02446/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 31 of its 58 references that are in the map.
- First posted on arXiv 5 Feb 2022.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Information-Theoretic Considerations in Batch Reinforcement Learning](https://mlsanity.com/paper/1905.00360/) (2019)
- [A Theory of Regularized Markov Decision Processes](https://mlsanity.com/paper/1901.11275/) (2019)
- [Bellman-consistent Pessimism for Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06926/) (2021)
- [A unified view of entropy-regularized Markov decision processes](https://mlsanity.com/paper/1705.07798/) (2017)
- [Safe Policy Improvement with Baseline Bootstrapping](https://mlsanity.com/paper/1712.06924/) (2017)
- [Representation Learning for Online and Offline RL in Low-rank MDPs](https://mlsanity.com/paper/2110.04652/) (2021)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning](https://mlsanity.com/paper/2108.08812/) (2021)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [Provably Good Batch Reinforcement Learning Without Great Exploration](https://mlsanity.com/paper/2007.08202/) (2020)
- [A Game Theoretic Framework for Model Based Reinforcement Learning](https://mlsanity.com/paper/2004.07804/) (2020)
- [Heuristic-Guided Reinforcement Learning](https://mlsanity.com/paper/2106.02757/) (2021)
- [Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2110.14000/) (2021)
- [Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison](https://mlsanity.com/paper/2003.03924/) (2020)
- [Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms](https://mlsanity.com/paper/2109.12286/) (2021)

## Built on by (most cited first, 30 of 111)

- [Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons](https://mlsanity.com/paper/2301.11270/) (2023)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [Is Value Learning Really the Main Bottleneck in Offline RL?](https://mlsanity.com/paper/2406.09329/) (2024)
- [On Penalty-based Bilevel Gradient Descent Method](https://mlsanity.com/paper/2302.05185/) (2023)
- [RORL: Robust Offline Reinforcement Learning via Conservative Smoothing](https://mlsanity.com/paper/2206.02829/) (2022)
- [The Role of Coverage in Online Reinforcement Learning](https://mlsanity.com/paper/2210.04157/) (2022)
- [Robust Preference Optimization through Reward Model Distillation](https://mlsanity.com/paper/2405.19316/) (2024)
- [Provable Offline Preference-Based Reinforcement Learning](https://mlsanity.com/paper/2305.14816/) (2023)
- [Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage](https://mlsanity.com/paper/2305.09659/) (2023)
- [Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking](https://mlsanity.com/paper/2403.03185/) (2024)
- [Dual RL: Unification and New Methods for Reinforcement and Imitation Learning](https://mlsanity.com/paper/2302.08560/) (2023)
- [Behavior Proximal Policy Optimization](https://mlsanity.com/paper/2302.11312/) (2023)
- [Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2309.12696/) (2023)
- [Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2209.06620/) (2022)
- [Data-Driven Offline Decision-Making via Invariant Representation Learning](https://mlsanity.com/paper/2211.11349/) (2022)
- [Adversarial Model for Offline Reinforcement Learning](https://mlsanity.com/paper/2302.11048/) (2023)
- [Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian](https://mlsanity.com/paper/2211.00716/) (2022)
- [The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning](https://mlsanity.com/paper/2305.15703/) (2023)
- [Hindsight Learning for MDPs with Exogenous Inputs](https://mlsanity.com/paper/2207.06272/) (2022)
- [When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning](https://mlsanity.com/paper/2302.07457/) (2023)
- [Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization](https://mlsanity.com/paper/2311.03351/) (2023)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [Towards Robust Offline Reinforcement Learning under Diverse Data Corruption](https://mlsanity.com/paper/2310.12955/) (2023)
- [One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2212.00124/) (2022)
- [Benchmarking Offline Reinforcement Learning on Real-Robot Hardware](https://mlsanity.com/paper/2307.15690/) (2023)
- [On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2211.13208/) (2022)
- [Doubly Mild Generalization for Offline Reinforcement Learning](https://mlsanity.com/paper/2411.07934/) (2024)
- [Survival Instinct in Offline Reinforcement Learning](https://mlsanity.com/paper/2306.03286/) (2023)
- [Supported Trust Region Optimization for Offline Reinforcement Learning](https://mlsanity.com/paper/2311.08935/) (2023)

## Abstract (arXiv)

We propose Adversarially Trained Actor Critic (ATAC), a new model-free algorithm for offline reinforcement learning (RL) under insufficient data coverage, based on the concept of relative pessimism. ATAC is designed as a two-player Stackelberg game: A policy actor competes against an adversarially trained value critic, who finds data-consistent scenarios where the actor is inferior to the data-collection behavior policy. We prove that, when the actor attains no regret in the two-player game, running ATAC produces a policy that provably 1) outperforms the behavior policy over a wide range of hyperparameters that control the degree of pessimism, and 2) competes with the best policy covered by data with appropriately chosen hyperparameters. Compared with existing works, notably our framework offers both theoretical guarantees for general function approximation and a deep RL implementation scalable to complex environments and large datasets. In the D4RL benchmark, ATAC consistently outperforms state-of-the-art offline RL algorithms on a range of continuous control tasks.