TRIRL enables explicit dual-ascent IRL via trust-region local policy updates that guarantee monotonic improvement without full RL solves per iteration, outperforming prior imitation methods by 2.4x aggregate IQM and recovering generalizable rewards.
arXiv preprint arXiv:1807.06158 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from a large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and also a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We conduct experiments in two different settings: (1) when demonstrations consist of low-dimensional, manually-defined state features, and (2) when demonstrations consist of high-dimensional, raw visual data. We demonstrate that our approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
XIPER creates a reward signal for cross-domain video imitation learning by training a video prediction model that maps agent views to the expert domain and scoring prediction likelihood.
citing papers explorer
-
Reinforcement Learning from Cross-domain Videos with Video Prediction Model
XIPER creates a reward signal for cross-domain video imitation learning by training a video prediction model that maps agent views to the expert domain and scoring prediction likelihood.