Rapidly Adaptable Legged Robots Via Evolutionary Meta-Learning
IEEE/RJS International Conference on Intelligent RObots and Systems (IROS)(2020)CCF C
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

MELD: Meta-Reinforcement Learning from Images Via Latent State Models.
被引用19
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms.
被引用30
Evolving Gaits for Damage Control in a Hexapod Robot.
被引用4
RMA: Rapid Motor Adaptation for Legged Robots
被引用205
Behavior Self-Organization Supports Task Inference for Continual Robot Learning
被引用17
Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey
被引用15
Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains
被引用4
Robust Policy Learning over Multiple Uncertainty Sets.
被引用17
A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization
被引用11
I-Sim2real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops.
被引用5
PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
被引用12
Model-free End-to-end Learning of Agile Quadrupedal Locomotion over Challenging Terrain.
被引用2
Probabilistic Meta-Conv1D Driving Energy Prediction for Mobile Robots in Unstructured Terrains.
被引用1
Assisted Operation of a Robotic Arm Based on Stereo Vision for Positioning Near an Explosive Device
被引用9
MODEL-AGNOSTIC META-LEARNING FOR RESILIENCE OPTIMIZATION OF ARTIFICIAL INTELLIGENCE SYSTEM
被引用1
被引用3
Efficient Dynamic Locomotion of Quadruped Robot Via Adaptive Diagonal Gait
被引用1
Sim-to-Real Transfer for Quadrupedal Locomotion Via Terrain Transformer.
被引用4
Evolutionary Machine Learning in Robotics
被引用0
Meta-Learning with Evolutionary Strategy for Resilience Optimization of Image Recognition System
被引用0