paper-with-me

홈 › Papers

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

2021-10-22 · ICLR 2022 4 · Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez

Goal-conditioned reinforcement learning (RL) can solve tasks in a wide range of domains, including navigation and manipulation, but learning to reach distant goals remains a central challenge to the field. Learning to reach such goals is particularly hard without any offline data, expert demonstrations, and reward shaping. In this paper, we propose an algorithm to solve the distant goal-reaching task by using search at training time to automatically generate a curriculum of intermediate states. Our algorithm, Classifier-Planning (C-Planning), frames the learning of the goal-conditioned policies as expectation maximization: the E-step corresponds to planning an optimal sequence of waypoints using graph search, while the M-step aims to learn a goal-conditioned policy to reach those waypoints. Unlike prior methods that combine goal-conditioned RL with graph search, ours performs search only during training and not testing, significantly decreasing the compute costs of deploying the learned policy. Empirically, we demonstrate that our method is more sample efficient than prior methods. Moreover, it is able to solve very long horizons manipulation and navigation tasks, tasks that prior goal-conditioned methods and methods based on graph search fail to solve.

📄 PDF Abstract BibTeX arXiv:2110.12080

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

CQM: Curriculum Reinforcement Learning with a Quantized World Model

2023-10-26 · NeurIPS 2023 11

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curri…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

SmoothTurn: Learning to Turn Smoothly for Agile Navigation with Quadrupedal Robots

2026-03-13 · Zunzhi You, Haolan Guo, Yunke Wang, Chang Xu arxiv

Quadrupedal robots show great potential for valuable real-world applications such as fire rescue and industrial inspection. Such applications often require urgency and the ability to navigate agilely, which in turn deman…

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

2019-06-12 · NeurIPS 2019 12 · Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine

The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning

2020-02-07 · Sha Luo, Hamidreza Kasaei, Lambert Schomaker

Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data p…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Region Growing Curriculum Generation for Reinforcement Learning

2018-07-04 · Artem Molchanov, Karol Hausman, Stan Birchfield, Gaurav Sukhatme

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)