Robust Imitation Learning Against Variations In Environment Dynamics

Abstract

In this paper, we propose a robust imitation learning (IL) framework that improves the robustness of IL when environment dynamics are perturbed. The existing IL framework trained in a single environment can catastrophically fail with perturbations in environment dynamics because it does not capture the situation that underlying environment dynamics can be changed. Our framework effectively deals with environments with varying dynamics by imitating multiple experts in sampled environment dynamics to enhance the robustness in general variations in environment dynamics. In order to robustly imitate the multiple sample experts, we minimize the risk with respect to the Jensen-Shannon divergence between the agent's policy and each of the sample experts. Numerical results show that our algorithm significantly improves robustness against dynamics perturbations compared to conventional IL baselines.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychae2022robust

Related papers

• State-only Imitation With Transition Dynamics Mismatch (2020)0.00
• Invariant Causal Imitation Learning For Generalizable Policies (2023)0.00
• Sample-efficient Robust Multi-agent Reinforcement Learning In The Face Of Environmental Uncertainty (2024)0.00
• Conditional Kernel Imitation Learning For Continuous State Environments (2023)0.00
• Causal Imitation Learning Under Temporally Correlated Noise (2022)0.00
• Provably Efficient Adversarial Imitation Learning With Unknown Transitions (2023)0.00
• Bayesian Robust Optimization For Imitation Learning (2020)0.00
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00