Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning

TL;DR

This paper introduces a dynamic method to combine reinforcement learning and imitation learning, improving sample efficiency and policy performance in local planning for mobile robots by adaptively weighting learning signals during training.

Contribution

It presents a novel performance-based modulation technique that smoothly transitions from imitation to reinforcement learning, enhancing learning efficiency and policy effectiveness.

Findings

Achieves 4x sample efficiency over pure RL.

Attains an average success rate of 0.959 in local planning tasks.

Successfully deploys policies in real-world scenarios without fine-tuning.

Abstract

This paper proposes a method to combine reinforcement learning (RL) and imitation learning (IL) using a dynamic, performance-based modulation over learning signals. The proposed method combines RL and behavioral cloning (IL), or corrective feedback in the action space (interactive IL/IIL), by dynamically weighting the losses to be optimized, taking into account the backpropagated gradients used to update the policy and the agent's estimated performance. In this manner, RL and IL/IIL losses are combined by equalizing their impact on the policy's updates, while modulating said impact such that IL signals are prioritized at the beginning of the learning process, and as the agent's performance improves, the RL signals become progressively more relevant, allowing for a smooth transition from pure IL/IIL to pure RL. The proposed method is used to learn local planning policies for mobile robots, synthesizing IL/IIL signals online by means of a scripted policy. An extensive evaluation of the application of the proposed method to this task is performed in simulations, and it is empirically shown that it outperforms pure RL in terms of sample efficiency (achieving the same level of performance in the training environment utilizing approximately 4 times less experiences), while consistently producing local planning policies with better performance metrics (achieving an average success rate of 0.959 in an evaluation environment, outperforming pure RL by 12.5% and pure IL by 13.9%). Furthermore, the obtained local planning policies are successfully deployed in the real world without performing any major fine tuning. The proposed method can extend existing RL algorithms, and is applicable to other problems for which generating IL/IIL signals online is feasible. A video summarizing some of the real world experiments that were conducted can be found in https://youtu.be/mZlaXn9WGzw.