REVIEW 6 cited by
Residual Reinforcement Learning from Demonstrations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn from visual inputs and sparse rewards using demonstrations. Learning from images, proprioceptive inputs and a sparse task-completion reward relaxes the requirement of accessing full state features, such as object and target positions. In addition, replacing the base controller with a policy learned from demonstrations removes the dependency on a hand-engineered controller in favour of a dataset of demonstrations, which can be provided by non-experts. Our experimental evaluation on simulated manipulation tasks on a 6-DoF UR5 arm and a 28-DoF dexterous hand demonstrates that residual RL from demonstrations is able to generalize to unseen environment conditions more flexibly than either behavioral cloning or RL fine-tuning, and is capable of solving high-dimensional, sparse-reward tasks out of reach for RL from scratch.
Forward citations
Cited by 6 Pith papers
-
C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video
C2Dex converts monocular human videos into executable dexterous robot manipulation trajectories by using stable object-side contacts as a shared representation for reconstruction and retargeting, achieving 57.78% and ...
-
Touch begins where vision ends: Generalizable policies for contact-rich manipulation
A localize-then-execute policy that combines vision-language reaching, semantic background augmentation, and residual reinforcement learning with tactile sensing reaches about 90% success on millimeter-precision manip...
-
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Offline residual SAC correction on CNN–LSTM kinematic outputs improves continuous 3D EEG motor-imagery decoding by ~21–42% in correlation and RMSE across 2D and VR feedback without feeding EEG to the RL agent.
-
Residual Reward Models for Preference-based Reinforcement Learning
Combining a hand-designed or learned prior reward with a preference-trained residual improves sample efficiency and final performance in preference-based reinforcement learning.
-
ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
ASAP trains a residual action model on real-world rollouts and fine-tunes simulation policies through it, reducing humanoid whole-body motion tracking error in sim-to-real transfer.
-
Learning-based Autonomous Oversteer Control and Collision Avoidance
QC-SAC reaches 81.8% success on a new simulated oversteer-plus-obstacle-avoidance benchmark, beating BC, SAC, and BC-SAC baselines.
Discussion (0). Continue with ORCID to comment.