Privileged Knowledge Distillation for Sim-to-Real Policy Generalization

by   Haoran He, et al.

Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most RL methods operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the privileged knowledge, resulting in suboptimal performance. In this paper, we propose a novel single-stage privileged knowledge distillation method called the Historical Information Bottleneck (HIB) to narrow the sim-to-real gap. In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods.


Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

Off-policy ensemble reinforcement learning (RL) methods have demonstrate...

DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration

Reinforcement learning (RL) has demonstrated great success in the past s...

KnowRU: Knowledge Reusing via Knowledge Distillation in Multi-agent Reinforcement Learning

Recently, deep Reinforcement Learning (RL) algorithms have achieved dram...

Reinforcement Learning of a CPG-regulated Locomotion Controller for a Soft Snake Robot

In this work, we present a learning-based goal-tracking control method f...

Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning

In real-world applications of reinforcement learning (RL), noise from in...

Please sign up or login with your details

Forgot password? Click here to reset