TRIRL enables explicit dual-ascent IRL via trust-region local policy updates that guarantee monotonic improvement without full RL solves per iteration, outperforming prior imitation methods by 2.4x aggregate IQM and recovering generalizable rewards.
International conference on machine learning , pages=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8verdicts
UNVERDICTED 8representative citing papers
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
TBPO derives a token-level preference optimization objective from sequence-level pairwise data via Bregman divergence ratio matching that generalizes DPO and improves alignment quality.
HölderPO unifies token aggregation in GRPO via the Hölder mean with dynamic p annealing, reporting 54.9% average math-benchmark accuracy and 93.8% ALFWorld success.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
MARS replaces additive clipping and soft penalties in multi-agent trust-region methods with a symmetric geometric barrier, matching or exceeding MAPPO and MASPO performance across 47 tasks in eight environments.
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
citing papers explorer
-
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
TRIRL enables explicit dual-ascent IRL via trust-region local policy updates that guarantee monotonic improvement without full RL solves per iteration, outperforming prior imitation methods by 2.4x aggregate IQM and recovering generalizable rewards.
-
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
TBPO derives a token-level preference optimization objective from sequence-level pairwise data via Bregman divergence ratio matching that generalizes DPO and improves alignment quality.
-
H\"older Policy Optimisation
HölderPO unifies token aggregation in GRPO via the Hölder mean with dynamic p annealing, reporting 54.9% average math-benchmark accuracy and 93.8% ALFWorld success.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
MARS replaces additive clipping and soft penalties in multi-agent trust-region methods with a symmetric geometric barrier, matching or exceeding MAPPO and MASPO performance across 47 tasks in eight environments.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.