DeepAI AI Chat
Log In Sign Up

Guided Curriculum Learning for Walking Over Complex Terrain

by   Brendan Tidd, et al.

Reliable bipedal walking over complex terrain is a challenging problem, using a curriculum can help learning. Curriculum learning is the idea of starting with an achievable version of a task and increasing the difficulty as a success criteria is met. We propose a 3-stage curriculum to train Deep Reinforcement Learning policies for bipedal walking over various challenging terrains. In the first stage, the agent starts on an easy terrain and the terrain difficulty is gradually increased, while forces derived from a target policy are applied to the robot joints and the base. In the second stage, the guiding forces are gradually reduced to zero. Finally, in the third stage, random perturbations with increasing magnitude are applied to the robot base, so the robustness of the policies are improved. In simulation experiments, we show that our approach is effective in learning walking policies, separate from each other, for five terrain types: flat, hurdles, gaps, stairs, and steps. Moreover, we demonstrate that in the absence of human demonstrations, a simple hand designed walking trajectory is a sufficient prior to learn to traverse complex terrain types. In ablation studies, we show that taking out any one of the three stages of the curriculum degrades the learning performance.


Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control

We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for...

School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget

Pommerman is a hybrid cooperative/adversarial multi-agent environment, w...

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

Humans are highly adept at walking in environments with foot placement c...

Learning Bipedal Walking On Planned Footsteps For Humanoid Robots

Deep reinforcement learning (RL) based controllers for legged robots hav...

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning

Shaping in humans and animals has been shown to be a powerful tool for l...

Iterative Policy-Space Expansion in Reinforcement Learning

Humans and animals solve a difficult problem much more easily when they ...

Virtual pivot point in human walking: always experimentally observed but simulations suggest it may not be necessary

The intersection of ground reaction forces in a small, point-like area a...