Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
Reward-conditioned policies
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
QGF performs test-time policy optimization for flow models in RL by guiding a behavior-cloned reference policy with value-function gradients, achieving strong results on high-dimensional offline RL benchmarks without additional policy training.
Proposes attention-based sparse evidence learning and a preference-conditioned stopping policy that improves early failure alerting Pareto frontiers by 3-42% over prior methods on five dialog and agent benchmarks.
FPL trains a language-conditioned reward model from per-axis human preferences and a reward-conditioned policy, reporting 38-point average success gains over sparse-reward and binary-preference baselines on six manipulation tasks.
FlowR2A learns reward-conditioned action distributions via flow-matching decoder to unify dense reward supervision with dynamic proposal generation for multimodal driving planning.
A neuro-symbolic framework compiles LTLf formulas to DFAs, derives differentiable satisfaction signals from DFA progression, and uses them as a logic-based regularization loss to enforce temporal constraints in autoregressive transformer RL policies while preserving competitive returns.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
citing papers explorer
-
Decision Transformer: Reinforcement Learning via Sequence Modeling
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
-
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
QGF performs test-time policy optimization for flow models in RL by guiding a behavior-cloned reference policy with value-function gradients, achieving strong results on high-dimensional offline RL benchmarks without additional policy training.
-
When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories
Proposes attention-based sparse evidence learning and a preference-conditioned stopping policy that improves early failure alerting Pareto frontiers by 3-42% over prior methods on five dialog and agent benchmarks.
-
Freeform Preference Learning for Robotic Manipulation
FPL trains a language-conditioned reward model from per-axis human preferences and a reward-conditioned policy, reporting 38-point average success gains over sparse-reward and binary-preference baselines on six manipulation tasks.
-
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
FlowR2A learns reward-conditioned action distributions via flow-matching decoder to unify dense reward supervision with dynamic proposal generation for multimodal driving planning.
-
Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies
A neuro-symbolic framework compiles LTLf formulas to DFAs, derives differentiable satisfaction signals from DFA progression, and uses them as a logic-based regularization loss to enforce temporal constraints in autoregressive transformer RL policies while preserving competitive returns.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
RISE: Self-Improving Robot Policy with Compositional World Model
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
Is Conditional Generative Modeling all you need for Decision-Making?
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.