Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
The safety of autonomous vehicles (AV) has been a long-standing top concern, stemming
from the absence of rare and safety-critical scenarios in the long-tail naturalistic driving …
from the absence of rare and safety-critical scenarios in the long-tail naturalistic driving …
A Pilot Study of Observation Poisoning on Selective Reincarnation in Multi-Agent Reinforcement Learning
H Putla, C Patibandla, KP Singh… - Neural Processing …, 2024 - Springer
This research explores the vulnerability of selective reincarnation, a concept in Multi-Agent
Reinforcement Learning (MARL), in response to observation poisoning attacks. Observation …
Reinforcement Learning (MARL), in response to observation poisoning attacks. Observation …
Learn to Teach: Improve Sample Efficiency in Teacher-student Learning for Sim-to-Real Transfer
Simulation-to-reality (sim-to-real) transfer is a fundamental problem for robot learning.
Domain Randomization, which adds randomization during training, is a powerful technique …
Domain Randomization, which adds randomization during training, is a powerful technique …
Curriculum Is More Influential Than Haptic Information During Reinforcement Learning of Object Manipulation Against Gravity
P Ojaghi, R Mir, A Marjaninejad, A Erwin… - arXiv preprint arXiv …, 2024 - arxiv.org
Learning to lift and rotate objects with the fingertips is necessary for autonomous in-hand
dexterous manipulation. In our study, we explore the impact of various factors on successful …
dexterous manipulation. In our study, we explore the impact of various factors on successful …
Learning to Explore in POMDPs with Informational Rewards
Standard exploration methods typically rely on random coverage of the state space or
coverage-promoting exploration bonuses. However, in partially observed settings, the …
coverage-promoting exploration bonuses. However, in partially observed settings, the …