Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Deep Soft Q-learning”
Paper proposes a pretraining method for soft Q-learning from imperfect demonstrations.
problem Challenges in exploiting expert demonstrations while maintaining exploration potentials.
method γ-discounted biased policy evaluation with entropy regularization.
result Our method effectively learns from imperfect demonstrations and outperforms other methods.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
Adversarial learning tackles unnormalized densities without samples.
problem Learning from unnormalized densities without direct samples.
method Adversarial learning extended to unnormalized densities, with new GAN regularization concepts.
result Encouraging results across applications, including deep soft Q-learning.
Boosts Q-learning by using value function bounds.
problem Efficiently solving new tasks using past experience.
method Derives double-sided bounds on optimal value function and uses them to update Q-function.
result Boosted training performance through alternative Q-function update method.
A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.
problem Stabilizing model-free off-policy deep reinforcement learning with soft divergence.
method Representing past experiences as a QGraph, selecting a subgraph with favorable structure, and using lower bounds for temporal difference learning.
result QG-DDPG method is less prone to soft divergence and more robust to hyperparameters.
Paper proposes methods to use observational data for reinforcement learning, addressing confounding issues.
problem Using observational data for reinforcement learning can lead to misleading outcomes due to unobserved confounders.
method The paper introduces two deconfounding methods in deep reinforcement learning to adjust for confounders.
result The proposed deconfounding methods improve the accuracy of reinforcement learning models using observational data.
Neural TD and Q-learning prove to converge globally to optimal solutions.
problem Nonconvexity and divergence in neural TD due to value function approximation.
method Proving global convergence of neural TD and Q-learning using overparametrization of neural networks.
result Neural TD and Q-learning converge globally to the global optimum of mean-squared projected Bellman error.
The paper analyzes the convergence rates of Q-learning with entropy regularization and linear function approximation.
problem Analyzing the convergence rates of Q-learning with entropy regularization and linear function approximation.
method The paper derives rates of convergence using the high-dimensional central limit theorem, linearization of the soft Bellman recursion, and Gaussian approximation for the leading martingale term.
result The algorithm's last iterate satisfies high-order moment bounds, with a Gaussian approximation bound of order .
Temporal-difference and Q-learning learn feature representations that converge to optimal ones.
problem Understanding how feature representations evolve in temporal-difference and Q-learning with neural networks.
method Mean-field theory applied to overparameterized two-layer neural networks.
result The feature representation converges to the optimal one, generalizing previous results.
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcs.LG
Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and brittle convergence properties, which necessitate meticulous hyperparameter tuning…
SUNRISE improves off-policy RL algorithms by integrating ensemble methods.
problem Stability and exploration issues in off-policy RL algorithms.
method SUNRISE combines ensemble-based weighted Bellman backups and upper-confidence bounds for efficient exploration.
result SUNRISE improves the performance of off-policy RL algorithms across various domains.
Proposes a new Deep Recurrent Double Q-Learning model for Atari games.
problem Improving Deep Reinforcement Learning models for Atari games.
method Integrates Double Q-Learning and Recurrent Networks (LSTM, DRQN) for Atari games.
result Demonstrates improved performance in Atari games compared to existing models.
New dropout technique reduces variance and overestimation in deep Q-Learning.
problem Reduction of variance and overestimation in deep Q-Learning.
method Using Dropout techniques to reduce variance and overestimation in deep Q-Learning.
result Demonstrated effectiveness in enhancing stability and reducing both variance and overestimation.
DSAC improves robustness of imitation learning.
problem Learning from few expert data and distribution shift.
method DSAC uses adversarial reward function.
result DSAC performs well on PyBullet environments.
Deep Q-learning generates directed acyclic graphs.
problem Generating DAGs with specified structures.
method Deep reinforcement learning, specifically deep Q-learning.
result Demonstrated capability of generating DAGs in sparse reward environments.
Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methodscs.LG
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
problem Underestimation bias in deep actor-critic methods for reinforcement learning.
method Introduces a parameter-free Q-learning variant that combines maximum and minimum operators to bound value estimates.
result Improves state-of-the-art performance on OpenAI Gym tasks.
Improved deep Q-learning with SVRG reduces variance and stabilizes training.
problem Excessive variance in gradient estimation hinders deep Q-learning performance.
method Utilized stochastic variance reduced gradient (SVRG) techniques.
result Significantly improved performance on 18 out of 20 Atari games compared to baseline methods.
Theoretical analysis improves understanding of Deep Q-Learning's behavior.
problem Lack of formal guarantees and gaps between theory and practice of Deep Q-Learning.
method Dynamical systems perspective, focusing on realistic assumptions.
result Proves convergence of Deep Q-Learning under specific conditions.
The paper uses potential functions to help reinforcement learning agents learn optimal policies.
problem Learning optimal stochastic policies in reinforcement learning.
method Augmenting the reward with potential functions and applying these to policy gradient algorithms.
result Potential-based reward shaping preserves optimality of stochastic policies and speeds up learning.
Enhances SAC for better sample efficiency in continuous-action tasks.
problem Improving sample efficiency in soft actor-critic algorithms.
method Integrating Emphasizing Recent Experience (ERE) with Soft Actor-Critic (SAC) and Priority Experience Replay (PER).
result ERE significantly improves sample efficiency compared to vanilla SAC, especially for continuous-action tasks.
Proposes a deep spectral Q-learning for mobile health data.
problem Personalized treatment assignment for patients with time-varying covariates.
method Integrates PCA with deep Q-learning for mixed frequency data.
result Mean return converges to optimal under estimated optimal policy.
Deep Q-learning methods are sensitive to time discretization, which this paper addresses.
problem Sensitivity of Deep Q-learning methods to time discretization in near continuous-time environments.
method Identified and formalized the problem of sensitivity to time discretization. Developed a principled off-policy RL algorithm.
result Proved that Q-learning does not exist in continuous time and developed a robust algorithm.
EBQL reduces bias in Q-learning for improved performance.
problem Over- and under-estimation biases in Q-learning degrade performance.
method Ensemble Bootstrapping to reduce both over- and under-estimation biases.
result EBQL outperforms other Q-learning methods in Atari games.
Reverse Experience Replay improves Deep Q-learning for sparse rewards.
problem Sparse rewards and reward-maximizing tasks in Deep Q-learning.
method Sampling transitions in reverse order for training.
result Significantly increased performance in tasks with limited experience and memory capacity.
New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
problem Offline RL with limited exploration and assumptions about data coverage and Q-function realizability.
method Proposes minimax learning algorithms to estimate soft or vanilla Q-functions with -convergence guarantees.
result PAC guarantees for offline RL under partial coverage and realizability conditions.
Paper analyzes Q-learning with neural networks, proving a fast convergence rate.
problem Analyzing the convergence rate of neural Q-learning.
method Finite-time analysis of neural Q-learning with a deep ReLU network.
result Neural Q-learning converges to optimal policy with rate.
Paper automates car negotiation in intersections using Q-learning.
problem Automated vehicles negotiate with human-driven cars in intersections.
method Deep Q-learning applied to simulated traffic with various driver behaviors.
result 98% success rate in avoiding collisions with other vehicles.
Periodic Q-Learningcs.LG
PQ-learning improves Q-learning by periodically updating target estimates.
problem Improving sample complexity in Q-learning for finding optimal policies.
method Maintains two Q-value estimates, one online and one target, updated periodically.
result PQ-learning achieves better sample complexity for finding epsilon-optimal policies.
Investigates Q-learning bottlenecks with function approximation and sampling methods.
problem Understanding and mitigating issues in Q-learning with function approximation.
method Unit testing framework with oracles to disentangle sources of error; novel sampling method based on function approximation error.
result Large neural networks improve learning stability and offer practical compensations for overfitting.
Deep Q-learning analyzes EEG for drowsiness during driving tests.
problem Estimating drowsiness during driving to improve safety.
method Adapting Q-learning to EEG data for drowsiness estimation.
result Trained model accurately tracks mind state variations in EEG data.
A new algorithm SRG-DQN reduces variance in deep Q-learning.
problem Inaccurate estimation of anchor points in SVRG for deep Q-learning.
method Introduces recursive gradient variance reduction for stochastic gradient updates.
result Demonstrates improved efficiency and effectiveness of SRG-DQN on reinforcement learning tasks.
ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.
problem Delusional bias in deep Q-learning.
method Efficient methods to mitigate delusional bias by training Q-approximators with consistent labels and a search framework.
result Improves performance in Atari games, sometimes dramatically.
A new algorithm for deep Q-learning with robustness to state transition uncertainty.
problem Model uncertainty in state transitions for non-tabular, continuous state spaces.
method Distributionally robust approach using worst-case transition ball and dualized Bellman operator with Sinkhorn distance.
result Optimal policy found through solving non-linear Bellman equation with neural network parameterization.
Soft labeling impacts OOD detection in neural networks.
problem Impact of soft labeling on OOD detection in deep neural networks.
method Empirical analysis of how soft labeling affects OOD detection performance.
result Soft labeling can either improve or deteriorate OOD detection performance.
Deep Q-Learning method for Nash equilibria in stochastic games.
problem Model-free learning for multi-agent stochastic games, especially for general-sum games.
method Data-efficient Deep-Q-learning using local linear-quadratic expansion parametrized by deep neural networks.
result The algorithm learns optimal actions for stochastic games without experiencing all state-action pairs.
Deep Q-learning optimizes same-day delivery with vehicles and drones.
problem Optimizing same-day delivery with limited vehicle and drone capacities.
method Deep Q-learning approach to assign packages to vehicles or drones.
result Deep Q-learning policy outperforms benchmark policies and maintains effectiveness with changing fleet sizes.
Proposes a new method for deep ensembles that improves accuracy and calibration.
problem Improving accuracy and calibration of deep ensembles.
method Estimates confusion matrices of ensemble members and weighs them according to their inferred performance.
result Empirically shows superiority of soft Dawid Skene over ensemble averaging.
New target-based TD learning algorithms improve deep Q-learning convergence.
problem Improving convergence of deep Q-learning algorithms.
method Introducing averaging TD, double TD, and periodic TD algorithms.
result Established asymptotic convergence analyses for averaging TD and double TD, and finite sample analysis for periodic TD.
A new method for RL with continuous actions improves stability and scalability.
problem Stability and scalability issues in existing RL methods.
method Soft policy gradient with entropy regularization, combined with double sampling for soft Bellman equation.
result Outperforms off-policy prior methods in continuous action RL tasks.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
Soft-AE interprets autoencoders with adaptable wavelet units.
problem Lack of interpretability in autoencoders.
method Proposes Soft-AE with adaptable wavelet units and GenLU.
result Soft-AE offers interpretability and competitive performance.
Improved Q-learning for robot control with faster data-efficiency.
problem Poor data-efficiency and stochasticity in deep Q-learning.
method Composite Q-learning: Decomposes Q-function into short- and long-term predictions.
result Significant learning speedup and improved data-efficiency in robot tasks.
Deep Q-Learning model outperforms traditional methods in stock trading.
problem Optimal trade execution in stock markets.
method Model-free approach using Double Deep Q-Learning with neural networks.
result Model outperforms standard benchmark on most stocks.
A deep Q-learning method improves downlink power allocation in multi-cell networks.
problem Optimal resource allocation in dense, heterogeneous wireless networks is computationally challenging.
method Proposes a centralized DRL-based downlink power allocation scheme using deep Q-learning.
result The proposed DRL-based power allocation scheme outperforms conventional methods in multi-cell scenarios.
Improves deep neural networks using soft labels through alternating minimization.
problem Improving deep neural networks training with soft labels.
method Co-Learns DNNs and soft labels via Alternating Minimization of two objectives.
result COLAM achieves improved performance on many tasks with better testing classification accuracy.
Paper presents a new method for Bayesian deep learning that scales to Atari games.
problem Training neural networks on complex environments like Atari games is challenging.
method Adapted temporal difference Q-learning to work with Bayesian inference.
result TAGI allows for analytical inference of neural network parameters, achieving performance comparable to gradient-based methods.
Networked Control of Nonlinear Systems under Partial Observation Using Continuous Deep Q-Learningcs.LG
A controller learns to control a nonlinear plant with unknown model and partial observation using continuous deep Q-learning.
problem Designing a controller for a nonlinear plant with unknown model and partial sensor observation under network delays.
method Continuous deep Q-learning applied to an extended state including past control inputs and outputs.
result The controller can learn a robust control policy to network delays with partial sensor observation.