Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
131 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Mesh-based Tools to Analyze Deep Reinforcement Learning Policies for Underactuated Biped Locomotion (1903.12311v2)

Published 29 Mar 2019 in cs.RO and cs.SY

Abstract: In this paper, we present a mesh-based approach to analyze stability and robustness of the policies obtained via deep reinforcement learning for various biped gaits of a five-link planar model. Intuitively, one would expect that including perturbations and/or other types of noise during training would likely result in more robustness of the resulting control policy. However, one would also like to have a quantitative and computationally-efficient means of evaluating the degree to which this might be so. Rather than relying on Monte Carlo simulations, which can become quite computationally burdensome in quantifying performance metrics, our goal is to provide more sophisticated tools to assess robustness properties of such policies. Our work is motivated by the twin hypotheses that contraction of dynamics, when achievable, can simplify the required complexity of a control policy and that control policies obtained via deep learning may therefore exhibit tendency to contract to lower-dimensional manifolds within the full state space, as a result. The tractability of our mesh-based tools in this work provides some evidence that this may be so.

Citations (4)

Summary

We haven't generated a summary for this paper yet.