Co-imitation Learning Without Expert Demonstration

Abstract

Imitation learning is a primary approach to improve the efficiency of reinforcement learning by exploiting the expert demonstrations. However, in many real scenarios, obtaining expert demonstrations could be extremely expensive or even impossible. To overcome this challenge, in this paper, we propose a novel learning framework called Co-Imitation Learning (CoIL) to exploit the past good experiences of the agents themselves without expert demonstration. Specifically, we train two different agents via letting each of them alternately explore the environment and exploit the peer agent's experience. While the experiences could be valuable or misleading, we propose to estimate the potential utility of each piece of experience with the expected gain of the value function. Thus the agents can selectively imitate from each other by emphasizing the more useful experiences while filtering out noisy ones. Experimental results on various tasks show significant superiority of the proposed Co-Imitat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyning2021co

Related papers

• Good Better Best: Self-motivated Imitation Learning For Noisy Demonstrations (2023)0.00
• Beyond-expert Performance With Limited Demonstrations: Efficient Imitation Learning With Double Exploration (2025)0.00
• A Dual Approach To Imitation Learning From Observations With Offline Datasets (2024)0.00
• A Bayesian Solution To The Imitation Gap (2024)0.00
• Independent Generative Adversarial Self-imitation Learning In Cooperative Multiagent Systems (2019)0.00
• Imitation Learning From Observation With Automatic Discount Scheduling (2023)0.00
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00
• Primal Wasserstein Imitation Learning (2020)0.00