# Adversarially Guided Actor-Critic

arXiv: https://arxiv.org/abs/2102.04376 · HTML: https://mlsanity.com/paper/2102.04376/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 8 Feb 2021.

## Builds on (most cited first, 30 of 45)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [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)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [A Theory of Regularized Markov Decision Processes](https://mlsanity.com/paper/1901.11275/) (2019)
- [Noisy Networks for Exploration](https://mlsanity.com/paper/1706.10295/) (2017)
- [Safe and Efficient Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1606.02647/) (2016)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Sample Efficient Actor-Critic with Experience Replay](https://mlsanity.com/paper/1611.01224/) (2016)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [Understanding the impact of entropy on policy optimization](https://mlsanity.com/paper/1811.11214/) (2018)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [Self-Imitation Learning](https://mlsanity.com/paper/1806.05635/) (2018)
- [RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments](https://mlsanity.com/paper/2002.12292/) (2020)

## Built on by (most cited first, 30 of 47)

- [MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research](https://mlsanity.com/paper/2109.13202/) (2021)
- [Exploration via Elliptical Episodic Bonuses](https://mlsanity.com/paper/2210.05805/) (2022)
- [Adversarial Intrinsic Motivation for Reinforcement Learning](https://mlsanity.com/paper/2105.13345/) (2021)
- [MADE: Exploration via Maximizing Deviation from Explored Regions](https://mlsanity.com/paper/2106.10268/) (2021)
- [Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality](https://mlsanity.com/paper/2205.13521/) (2022)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration](https://mlsanity.com/paper/2107.08966/) (2021)
- [A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs](https://mlsanity.com/paper/2306.03236/) (2023)
- [NAVIX: Scaling MiniGrid Environments with JAX](https://mlsanity.com/paper/2407.19396/) (2024)
- [Episodic Novelty Through Temporal Distance](https://mlsanity.com/paper/2501.15418/) (2025)
- [Diversifying AI: Towards Creative Chess with AlphaZero](https://mlsanity.com/paper/2308.09175/) (2023)
- [Learning General World Models in a Handful of Reward-Free Deployments](https://mlsanity.com/paper/2210.12719/) (2022)
- [LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward](https://mlsanity.com/paper/2210.05409/) (2022)
- [Exploring through Random Curiosity with General Value Functions](https://mlsanity.com/paper/2211.10282/) (2022)
- [Programmatic Reward Design by Example](https://mlsanity.com/paper/2112.08438/) (2021)
- [A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines](https://mlsanity.com/paper/2204.09772/) (2022)
- [An Evaluation Study of Intrinsic Motivation Techniques applied to Reinforcement Learning over Hard Exploration Environments](https://mlsanity.com/paper/2205.11184/) (2022)
- [Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks](https://mlsanity.com/paper/2309.16347/) (2023)
- [Constrained Ensemble Exploration for Unsupervised Skill Discovery](https://mlsanity.com/paper/2405.16030/) (2024)
- [The impact of intrinsic rewards on exploration in Reinforcement Learning](https://mlsanity.com/paper/2501.11533/) (2025)
- [Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness](https://mlsanity.com/paper/2105.09992/) (2021)
- [Improving Intrinsic Exploration by Creating Stationary Objectives](https://mlsanity.com/paper/2310.18144/) (2023)
- [Explore and Control with Adversarial Surprise](https://mlsanity.com/paper/2107.07394/) (2021)
- [Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing](https://mlsanity.com/paper/2402.02097/) (2024)
- [Constrained Intrinsic Motivation for Reinforcement Learning](https://mlsanity.com/paper/2407.09247/) (2024)
- [CALM: Curiosity-Driven Auditing for Large Language Models](https://mlsanity.com/paper/2501.02997/) (2025)
- [Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments](https://mlsanity.com/paper/2211.10515/) (2022)
- [Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems](https://mlsanity.com/paper/2211.13742/) (2022)
- [TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets](https://mlsanity.com/paper/2212.02125/) (2022)
- [Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation](https://mlsanity.com/paper/2211.16838/) (2022)

## Abstract (arXiv)

Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These methods consider a policy (the actor) and a value function (the critic) whose respective losses are built using different motivations and approaches. This paper introduces a third protagonist: the adversary. While the adversary mimics the actor by minimizing the KL-divergence between their respective action distributions, the actor, in addition to learning to solve the task, tries to differentiate itself from the adversary predictions. This novel objective stimulates the actor to follow strategies that could not have been correctly predicted from previous trajectories, making its behavior innovative in tasks where the reward is extremely rare. Our experimental analysis shows that the resulting Adversarially Guided Actor-Critic (AGAC) algorithm leads to more exhaustive exploration. Notably, AGAC outperforms current state-of-the-art methods on a set of various hard-exploration and procedurally-generated tasks.