mlsanityData to 7 Oct 2026

Addressing reward bias in Adversarial Imitation Learning with neutral reward functions

arXiv 2009.09467 ↗First posted 20 Sep 2020cs.LG cs.RO stat.MLcited by 4

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Generative Adversarial Imitation Learning suffers from the fundamental problem of reward bias stemming from the choice of reward functions used in the algorithm. Different types of biases also affect different types of environments - which are broadly divided into survival and task-based environments. We provide a theoretical sketch of why existing reward functions would fail in imitation learning scenarios in task based environments with multiple terminal states. We also propose a new reward function for GAIL which outperforms existing GAIL methods on task based environments with single and multiple terminal states and effectively overcomes both survival and termination bias.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 7 of its 16 references that are in the map. First posted on arXiv 20 Sep 2020.

Builds on

7 of 16 references.

Closest ancestors · 3

Same direction, newest first

  1. 2019Goal-conditioned Imitation Learning13 Jun
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  3. 2018Behavioral Cloning from Observation4 May

Other references · 4

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  4. 2017Imitating Driver Behavior with Generative Adversarial Networkscited by 92

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 0; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2024Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matchingcited by 10
  2. 2021A Pragmatic Look at Deep Imitation Learningcited by 9
  3. 2021Reward function shape exploration in adversarial imitation learning: an empirical studycited by 2
  4. 2026Learning from Demonstrations via Capability-Aware Goal Samplingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2020On Computation and Generalization of Generative Adversarial Imitation Learning
  2. 2025On Discovering Algorithms for Adversarial Imitation Learning
  3. 2023Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
  4. 2024Diffusion-Reward Adversarial Imitation Learning
  5. 2019Task-Relevant Adversarial Imitation Learning
  6. 2026Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
  7. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
  8. 2026Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms