Plan Your Target And Learn Your Skills: Transferable State-only Imitation Learning Via Decoupled Policy Optimization

Abstract

Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions. However, existing solutions only learn to extract a state-to-action mapping policy from the data, without considering how the expert plans to the target. This hinders the ability to leverage demonstrations and limits the flexibility of the policy. In this paper, we introduce Decoupled Policy Optimization (DePO), which explicitly decouples the policy as a high-level state planner and an inverse dynamics model. With embedded decoupled policy gradient and generative adversarial training, DePO enables knowledge transfer to different action spaces or state transition dynamics, and can generalize the planner to out-of-demonstration state regions. Our in-depth experimental analysis shows the effectiveness of DePO on learning a generalized target state planner while achieving the best imitation performance. We demon

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2022plan

Related papers

• State-only Imitation With Transition Dynamics Mismatch (2020)0.00
• Beyond-expert Performance With Limited Demonstrations: Efficient Imitation Learning With Double Exploration (2025)0.00
• Online Adaptation For Enhancing Imitation Learning Policies (2024)0.00
• A Dual Approach To Imitation Learning From Observations With Offline Datasets (2024)0.00
• Contextual Policy Transfer In Reinforcement Learning Domains Via Deep Mixtures-of-experts (2020)0.00
• A Simple Solution For Offline Imitation From Observations And Examples With Possibly Incomplete Trajectories (2023)0.00
• Think Outside The Policy: In-context Steered Policy Optimization (2025)0.00
• Transfer Learning Across Simulated Robots With Different Sensors (2019)0.00