TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control

• URL: http://arxiv.org/abs/2502.17322v1
• Date: Mon, 24 Feb 2025 16:55:27 GMT
• Title: TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control
• Authors: Zifeng Zhuang, Diyuan Shi, Runze Suo, Xiao He, Hongyin Zhang, Ting Wang, Shangke Lyu, Donglin Wang,
• Abstract summary: In general, feasible regions for accomplishing tasks within complex high-dimensional spaces are exceedingly narrow.<n>We propose the $textbfS$elf-$textbfI$mitative $textbfR$einforcement, where the RL algorithm also imitates potentially task-relevant trajectories.<n>Our proposed algorithm achieves 120% performance improvement on the challenging HumanoidBench with 5% extra computation overhead.
• Score: 26.93901849666341
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Complex high-dimensional spaces with high Degree-of-Freedom and complicated action spaces, such as humanoid robots equipped with dexterous hands, pose significant challenges for reinforcement learning (RL) algorithms, which need to wisely balance exploration and exploitation under limited sample budgets. In general, feasible regions for accomplishing tasks within complex high-dimensional spaces are exceedingly narrow. For instance, in the context of humanoid robot motion control, the vast majority of space corresponds to falling, while only a minuscule fraction corresponds to standing upright, which is conducive to the completion of downstream tasks. Once the robot explores into a potentially task-relevant region, it should place greater emphasis on the data within that region. Building on this insight, we propose the $\textbf{S}$elf-$\textbf{I}$mitative $\textbf{R}$einforcement $\textbf{L}$earning ($\textbf{SIRL}$) framework, where the RL algorithm also imitates potentially task-relevant trajectories. Specifically, trajectory return is utilized to determine its relevance to the task and an additional behavior cloning is adopted whose weight is dynamically adjusted based on the trajectory return. As a result, our proposed algorithm achieves 120% performance improvement on the challenging HumanoidBench with 5% extra computation overhead. With further visualization, we find the significant performance gain does lead to meaningful behavior improvement that several tasks are solved successfully.

Related papers

• Grammarization-Based Grasping with Deep Multi-Autoencoder Latent Space Exploration by Reinforcement Learning Agent [0.0]
  We propose a novel framework for robotic grasping based on the idea of compressing high-dimensional target and gripper features in a common latent space. Our approach simplifies grasping by using three autoencoders dedicated to the target, the gripper, and a third one that fuses their latent representations.
  arXiv  Detail & Related papers  (2024-11-13T12:26:08Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• DC-MRTA: Decentralized Multi-Robot Task Allocation and Navigation in Complex Environments [55.204450019073036]
  We present a novel reinforcement learning based task allocation and decentralized navigation algorithm for mobile robots in warehouse environments. We consider the problem of joint decentralized task allocation and navigation and present a two level approach to solve it. We observe improvement up to 14% in terms of task completion time and up-to 40% improvement in terms of computing collision-free trajectories for the robots.
  arXiv  Detail & Related papers  (2022-09-07T00:35:27Z)
• Overcoming Exploration: Deep Reinforcement Learning in Complex Environments from Temporal Logic Specifications [2.8904578737516764]
  We present a Deep Reinforcement Learning (DRL) algorithm for a task-guided robot with unknown continuous-time dynamics deployed in a large-scale complex environment. Our framework is shown to significantly improve performance (effectiveness, efficiency) and exploration of robots tasked with complex missions in large-scale complex environments.
  arXiv  Detail & Related papers  (2022-01-28T16:39:08Z)
• Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives [92.0321404272942]
  Reinforcement learning can be used to build general-purpose robotic systems. However, training RL agents to solve robotics tasks still remains challenging. In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
  arXiv  Detail & Related papers  (2021-10-28T17:59:30Z)
• On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game [140.19656665344917]
  We study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. We tackle this problem under the context of function approximation, leveraging powerful function approximators. We establish the first provably efficient reward-free RL algorithm with kernel and neural function approximators.
  arXiv  Detail & Related papers  (2021-10-19T07:26:33Z)
• Batch Exploration with Examples for Scalable Robotic Reinforcement Learning [63.552788688544254]
  Batch Exploration with Examples (BEE) explores relevant regions of the state-space guided by a modest number of human provided images of important states. BEE is able to tackle challenging vision-based manipulation tasks both in simulation and on a real Franka robot.
  arXiv  Detail & Related papers  (2020-10-22T17:49:25Z)
• Weakly-Supervised Reinforcement Learning for Controllable Behavior [126.04932929741538]
  Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. In many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. We introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks.
  arXiv  Detail & Related papers  (2020-04-06T17:50:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.