mlsanityData to 7 Oct 2026

Explorative Imitation Learning: A Path Signature Approach for Continuous Environments

arXiv 2407.04856 ↗First posted 5 Jul 2024cs.LG cs.AIcited by 3

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

Abstract (arXiv)

Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them.

Key facts. Cited by 3 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 16 of its 28 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

16 of 28 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024A Survey of Imitation Learning Methods, Environments and Metrics30 Apr
  2. 2024Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking1 Mar
  3. 2021Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap4 Mar
  4. 2021Off-Policy Imitation Learning from Observations25 Feb
  5. 2021MobILE: Model-Based Imitation Learning From Observation Alone22 Feb
  6. 2020Imitating Unknown Policies via Exploration13 Aug
  7. 2018Imitating Latent Policies from Observation21 May
  8. 2018Behavioral Cloning from Observation4 May

Other references · 8

  1. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  4. 2016A Primer on the Signature Method in Machine Learningcited by 100
  5. 2020Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUcited by 45
  6. 2017Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognitioncited by 20
  7. 2019RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstrationcited by 19
  8. 2020Augmented Behavioral Cloning from Observationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learningcited by 1
  2. 2025Quantifying Generalisation in Imitation Learningcited by 0
  3. 2026Online Goal Recognition using Path Signature and Dynamic Time Warpingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning from Observation: A Survey of Recent Advances
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2025Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
  4. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  5. 2019To Follow or not to Follow: Selective Imitation Learning from Observations
  6. 2021Imitation Learning: Progress, Taxonomies and Challenges
  7. 2023A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories
  8. 2019Recent Advances in Imitation Learning from Observation