Neural Dynamic Policies for End-to-End Sensorimotor Learning

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces. This forces the agent to make decisions at each point in training, and limits scalability to complex tasks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Meta-Learning MT50 NDP Average Success Rate 11% # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet