Learning Belief Representations for Imitation Learning in POMDPs

Tanmay Gangwani, Joel Lehman, Qiang Liu, Jian Peng

Research output: Contribution to journalConference articlepeer-review


We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been modeled using recurrent neural networks and probabilistic latent variable models, and shown to be effective for reinforcement learning in POMDPs. In this work, we investigate the belief representation learning problem for generative adversarial imitation learning in POMDPs. Instead of training the belief module and the policy separately as suggested in prior work, we learn the belief module jointly with the policy, using a task-aware imitation loss to ensure that the representation is more aligned with the policy’s objective. To improve robustness of representation, we introduce several informative belief regularization techniques, including multi-step prediction of dynamics and action-sequences. Evaluated on various partially observable continuous-control locomotion tasks, our belief-module imitation learning approach (BMIL) substantially outperforms several baselines, including the original GAIL algorithm and the task-agnostic belief learning algorithm. Extensive ablation analysis indicates the effectiveness of task-aware belief learning and belief regularization.

Original languageEnglish (US)
Pages (from-to)1061-1071
Number of pages11
JournalProceedings of Machine Learning Research
StatePublished - 2019
Externally publishedYes
Event35th Uncertainty in Artificial Intelligence Conference, UAI 2019 - Tel Aviv, Israel
Duration: Jul 22 2019Jul 25 2019

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Learning Belief Representations for Imitation Learning in POMDPs'. Together they form a unique fingerprint.

Cite this