Search Results for author:
Found 9 papers, 3 papers with code
Context-Former: Stitching via Latent Conditioned Sequence Modeling
On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance.
A dynamical clipping approach with task feedback for Proximal Policy Optimization
Different from previous clipping approaches, we consider increasing the maximum cumulative Return in reinforcement learning (RL) tasks as the preference of the RL task, and propose a bi-level proximal policy optimization paradigm, which involves not only optimizing the policy but also dynamically adjusting the clipping bound to reflect the preference of the RL tasks to further elevate the training outcomes and stability of PPO.
RSG: Fast Learning Adaptive Skills for Quadruped Robots by Skill Graph
Developing robotic intelligent systems that can adapt quickly to unseen wild situations is one of the critical challenges in pursuing autonomous robotics.
Sample Efficient Reward Augmentation in offline-to-online Reinforcement Learning
Offline-to-online RL can make full use of pre-collected offline datasets to initialize policies, resulting in higher sample efficiency and better performance compared to only using online algorithms alone for policy training.
STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
Due to the existence of similarity trap, such consistency regularization improperly enhances the consistency possiblity of the model's predictions between segment pairs, and thus reduces the confidence in reward learning, since the augmented distribution does not match with the original one in PbRL.
Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
Naturally, such a paradigm raises three core questions that are not fully answered by prior non-iterative offline RL counterparts like reward-conditioned policy: (q1) What information should we transfer from the inner-level to the outer-level?
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning
Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data.
RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
OOD exacerbates inconsistencies in magnitudes and directions of task gradients, which brings challenges for GBML to optimize the meta-knowledge by minimizing the sum of task gradients in each minibatch.
Behavior Proximal Policy Optimization
Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs.
