DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
Don’t change the algorithm, change the data: Exploratory data for offline reinforcement learning, 2022
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
Ring Attention uses blockwise computation and ring communication to let Transformers process sequences up to device-count times longer than prior memory-efficient methods.
ROVER pretrains transferable exploration policies by maximizing occupancy coverage with a learned resolvent world model and virtual sink state, outperforming baselines on sparse navigation tasks.
AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline RL.
SRCP improves zero-shot generalization of successor representation methods in visual unsupervised reinforcement learning via saliency-guided representations and consistency policies.
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
WestWorld introduces a scalable trajectory world model with Sys-MoE routing via system embeddings and structural embeddings for physical knowledge, pretrained on 89 environments to improve zero-shot prediction and real-robot control.
citing papers explorer
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
Ring Attention with Blockwise Transformers for Near-Infinite Context
Ring Attention uses blockwise computation and ring communication to let Transformers process sequences up to device-count times longer than prior memory-efficient methods.
-
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
ROVER pretrains transferable exploration policies by maximizing occupancy coverage with a learned resolvent world model and virtual sink state, outperforming baselines on sparse navigation tasks.
-
AdamO: A Collapse-Suppressed Optimizer for Offline RL
AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline RL.
-
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
SRCP improves zero-shot generalization of successor representation methods in visual unsupervised reinforcement learning via saliency-guided representations and consistency policies.
-
When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
-
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
WestWorld introduces a scalable trajectory world model with Sys-MoE routing via system embeddings and structural embeddings for physical knowledge, pretrained on 89 environments to improve zero-shot prediction and real-robot control.