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.
hub
Journal of Machine Learning Research , year =
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
DTSemNet gives an exact, invertible neural-network encoding of hard oblique decision trees that supports direct gradient training for both classification and regression without probabilistic softening or quantized estimators.
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
ICDN is a neural network that models log-demand from log-prices so elasticities can be derived exactly by differentiation, showing better out-of-sample performance than log-log benchmarks on beer sales data.
JAXenstein ports the Wolfenstein 3D engine to JAX to create a fast, scalable benchmark for first-person visual RL that is several times quicker than existing vision-based alternatives.
SAVGO unifies representation learning, value estimation, and policy optimization by embedding state-action pairs such that cosine similarity reflects action-value similarity, enabling similarity-kernel-guided policy improvement.
Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.
DQPOPE estimates the entire return distribution in off-policy evaluation via deep quantile process regression, providing statistical advantages over standard single-value methods with equivalent sample sizes.
KBSE learns policies and barrier functions iteratively via conditional mean embeddings to bound unsafe state reachability probabilities during exploration in deep RL.
A learned context-energy term in port-Hamiltonian policies creates selective risk navigation that activates evasive forces only when safer paths are available.
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.
-
Approximation-Free Differentiable Oblique Decision Trees
DTSemNet gives an exact, invertible neural-network encoding of hard oblique decision trees that supports direct gradient training for both classification and regression without probabilistic softening or quantized estimators.
-
Randomness is sometimes necessary for coordination
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
-
A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
Integrable Elasticity via Neural Demand Potentials
ICDN is a neural network that models log-demand from log-prices so elasticities can be derived exactly by differentiation, showing better out-of-sample performance than log-log benchmarks on beer sales data.
-
JAXenstein: Accelerated Benchmarking for First-Person Environments
JAXenstein ports the Wolfenstein 3D engine to JAX to create a fast, scalable benchmark for first-person visual RL that is several times quicker than existing vision-based alternatives.
-
SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control
SAVGO unifies representation learning, value estimation, and policy optimization by embedding state-action pairs such that cosine similarity reflects action-value similarity, enabling similarity-kernel-guided policy improvement.
-
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.
-
Distributional Off-Policy Evaluation with Deep Quantile Process Regression
DQPOPE estimates the entire return distribution in off-policy evaluation via deep quantile process regression, providing statistical advantages over standard single-value methods with equivalent sample sizes.
-
Kernel-Based Safe Exploration in Deep Reinforcement Learning
KBSE learns policies and barrier functions iteratively via conditional mean embeddings to bound unsafe state reachability probabilities during exploration in deep RL.
-
Learning Material-Aware Hamiltonian Risk Fields for Safe Navigation
A learned context-energy term in port-Hamiltonian policies creates selective risk navigation that activates evasive forces only when safer paths are available.