First in-orbit demonstration of a DRL-trained AI satellite attitude controller that performs robust inertial pointing after sim-to-real transfer.
super hub Mixed citations
Continuous control with deep reinforcement learning
Mixed citation behavior. Most common role is background (62%).
146
Pith papers citing it
Background
62% of classified citations
abstract
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algorithm robustly solves more than 20 simulated physics tasks, including classic problems such as cartpole swing-up, dexterous manipulation, legged locomotion and car driving. Our algorithm is able to find policies whose performance is competitive with those found by a planning algorithm with full access to the dynamics of the domain and its derivatives. We further demonstrate that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.
hub tools
citation-role summary
background 10
method 6
citation-polarity summary
claims ledger
- abstract We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algorithm robustly solves more than 20 simulated physics tasks, including classic problems such as cartpole swing-up, dexterous manipulation, legged locomotion and car driving. Our algorithm is able to find policies whose performance is competitive with those found by a planning algo
authors
co-cited works
representative citing papers
Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.
Generalized advantage estimation combined with trust region optimization enables stable neural network policy learning for complex continuous control from raw kinematics.
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.
Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
A training-free survival regression approach uses tabular foundation models to build an accelerated failure time model and iteratively impute right-censored data with a non-parametric in-context estimator, matching the performance of trained Cox and parametric AFT models on benchmarks.
Periodic and soft target updates guarantee convergence in linear Q-learning to the exact projected Q-Bellman solution under spectral and step-size conditions via joint spectral radius analysis of switched linear systems.
Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.
Wasserstein policy gradient converges globally in entropy-regularized RL via Bellman-induced distributional PL geometry and uniform LSI, yielding geometric contraction up to discretization bias.
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
A reference-decoupled reformulation makes direct data-driven LQT equivalent to certainty-equivalence solutions and supports convergent offline and online DeePO algorithms.
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.
A new marginalized reparameterization estimator allows low-variance training of mixture policies in entropy-regularized actor-critic algorithms, matching or exceeding Gaussian policy performance in several continuous control benchmarks.
The reciprocity gradient allows agents to learn near-optimal context-sensitive policies by analytically propagating reward gradients through reputation chains in multi-agent settings.
Derives loss-to-TV bounds providing probabilistic guarantees for GFlowNets and introduces Stable GFlowNets algorithm for improved training stability and distributional fidelity.
A new injective multi-jet framework for RL flow control provides jet-count-independent running cost upper bounds and enables superior coordinated jet strategies, achieving drag suppression beyond symmetric ideals on cylinders and aerodynamic efficiency gains from 53% to 73% on airfoils.
SRSD uses human-provided semantic labels to learn rewards that encourage reinforcement learning agents to discover a wide variety of meaningful and distinct behaviors.
Intentional TD and Intentional Policy Gradient select step sizes for fixed fractional TD error reduction and bounded policy KL divergence, yielding stable streaming deep RL performance on par with batch methods.
A model-free reinforcement learning agent learns to align crystals from diffraction images without human supervision or theoretical knowledge.
A litmus test based on reachset-conformant model identification and correlation analysis of uncertainties predicts if RL-based control is superior to model-based control without any RL training.
Action aliasing from safety projections harms policy-gradient estimates more severely when the projection is inside the policy than when it is outside, but a penalty term restores competitiveness.
Guided RL using Bezier curves and UARM model enables efficient, explainable omnidirectional jumping in quadruped robots.
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
citing papers explorer
-
Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics
Periodic and soft target updates guarantee convergence in linear Q-learning to the exact projected Q-Bellman solution under spectral and step-size conditions via joint spectral radius analysis of switched linear systems.
-
Variational Sequential Optimal Experimental Design using Reinforcement Learning
vsOED uses a variational one-point reward and RL policy optimization to provide a lower bound on expected information gain for sequential experimental design, supporting nuisance parameters, implicit likelihoods, and multiple design goals.
-
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.
-
Variational Proximal Policy Optimization
VP2O maps PPO to SVGD in a MoE architecture using functional kernels and expert orthogonalization, claiming +179 ELO on Codeforces and 32% token reduction on AIME for a 33B/4B model.