mlsanityData to 13 Oct 2026

ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning

arXiv 2211.04005 ↗First posted 8 Nov 2022cs.LG cs.AIcited by 1

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

Abstract (arXiv)

Given a dataset of expert agent interactions with an environment of interest, a viable method to extract an effective agent policy is to estimate the maximum likelihood policy indicated by this data. This approach is commonly referred to as behavioral cloning (BC). In this work, we describe a key disadvantage of BC that arises due to the maximum likelihood objective function; namely that BC is mean-seeking with respect to the state-conditional expert action distribution when the learner's policy is represented with a Gaussian. To address this issue, we introduce a modified version of BC, Adversarial Behavioral Cloning (ABC), that exhibits mode-seeking behavior by incorporating elements of GAN (generative adversarial network) training. We evaluate ABC on toy domains and a domain based on Hopper from the DeepMind Control suite, and show that it outperforms standard BC by being mode-seeking in nature.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 6 of its 9 references that are in the map. First posted on arXiv 8 Nov 2022.

Builds on

6 of 9 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning8 May
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep

Other references · 4

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,656
  2. 2015Continuous control with deep reinforcement learningcited by 3,290
  3. 2014Conditional Generative Adversarial Netscited by 2,157
  4. 2016Generative Adversarial Imitation Learningcited by 1,577

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Generalized Regression with Conditional GANscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Model-based Offline Imitation Learning with Non-expert Data
  2. 2018Behavioral Cloning from Observation
  3. 2022Planning for Sample Efficient Imitation Learning
  4. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
  5. 2026Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
  6. 2020Imitating Unknown Policies via Exploration
  7. 2022Diverse Imitation Learning via Self-Organizing Generative Models
  8. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Histories