paper-with-me

홈 › Papers

Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories

2021-05-07 · Mandy Xie, Anqi Li, Karl Van Wyk, Frank Dellaert, Byron Boots, Nathan Ratliff

Imitation learning (IL) is a frequently used approach for data-efficient policy learning. Many IL methods, such as Dataset Aggregation (DAgger), combat challenges like distributional shift by interacting with oracular experts. Unfortunately, assuming access to oracular experts is often unrealistic in practice; data used in IL frequently comes from offline processes such as lead-through or teleoperation. In this paper, we present a novel imitation learning technique called Collocation for Demonstration Encoding (CoDE) that operates on only a fixed set of trajectory demonstrations. We circumvent challenges with methods like back-propagation-through-time by introducing an auxiliary trajectory network, which takes inspiration from collocation techniques in optimal control. Our method generalizes well and more accurately reproduces the demonstrated behavior with fewer guiding trajectories when compared to standard behavioral cloning methods. We present simulation results on a 7-degree-of-freedom (DoF) robotic manipulator that learns to exhibit lifting, target-reaching, and obstacle avoidance behaviors.

📄 PDF Abstract BibTeX arXiv:2105.03019

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

Proximal Policy Optimization with Mixed Distributed Training

2019-07-15 · Zhen-Yu Zhang, Xiangfeng Luo, Tong Liu, Shaorong Xie 외

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algori…

Deep Reinforcement LearningReinforcement Learning

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup

2019-02-13 · Devin Schwab, Tobias Springenberg, Murilo F. Martins, Thomas Lampe 외

We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the rewar…

Imitation LearningReinforcement Learning

Learning Contraction Policies from Offline Data

2021-12-11 · Navid Rezazadeh, Maxwell Kolarich, Solmaz S. Kia, Negar Mehr

This paper proposes a data-driven method for learning convergent control policies from offline data using Contraction theory. Contraction theory enables constructing a policy that makes the closed-loop system trajectorie…

Data Augmentation

CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning

2024-05-02 · Kota Kondo, Andrea Tagliabue, Xiaoyi Cai, Claudius Tewari 외

Traditional optimization-based planners, while effective, suffer from high computational costs, resulting in slow trajectory generation. A successful strategy to reduce computation time involves using Imitation Learning …

Imitation LearningTrajectory Planning

Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization

2024-03-28 · Teodor V. Marinov, Alekh Agarwal, Mircea Trofin

This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong perform…

Compiler OptimizationImitation LearningReinforcement Learning (RL)