Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.
problem Vulnerability of deep reinforcement learning policies to adversarial perturbations.
method Analysis of deep reinforcement learning policy landscape and comparison of vanilla vs. adversarial training.
result Vanilla training yields more robust policies compared to adversarial training.
Study on adversarial training's impact on deep neural reinforcement learning policies.
problem Vulnerability of deep neural reinforcement learning policies to imperceptible adversarial perturbations.
method Two parallel approaches: Fourier spectrum analysis and feature sensitivity measurement.
result Adversarially trained policies are more sensitive to low frequency perturbations.
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
Combines soft greediness with Modified Policy Iteration for more efficient deep reinforcement learning.
problem Improving sample efficiency in deep reinforcement learning.
method Combines soft greediness with Modified Policy Iteration (MPI) for off-policy learning.
result The proposed algorithm is more sample efficient than original PPO and competitive with SAC.
Adversarial attacks can manipulate deep trading policies, compromising their performance.
problem Adversarial attacks can compromise deep reinforcement learning trading policies.
method Developed a threat model and proposed two attack techniques.
result Demonstrated the effectiveness of adversarial attacks against DQN trading agents.
Study shows code-level optimizations significantly impact deep RL algorithms.
problem Understanding the impact of implementation details on deep RL algorithms.
method Case study on PPO and TRPO, investigating the effects of code-level optimizations.
result Code-level optimizations are crucial for performance in deep RL algorithms.
Watermarks DRL policies with minimal performance impact.
problem Detecting and managing unauthorized use of proprietary DRL policies.
method Integrates a unique identifier into DRL policies' responses to a sequence of state transitions.
result Demonstrates feasibility with DQN policy in Cartpole environment.
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstab…
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
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.
Real-time policy distillation speeds up and improves reinforcement learning.
problem Slow and inefficient policy distillation in reinforcement learning.
method Simultaneous training and distillation of a teacher and student model.
result Significantly reduced distillation time and improved small model performance.
This paper merges deterministic policy gradient estimations to improve deep reinforcement learning performance.
problem The bias-variance tradeoff in estimating and using policy gradients for deep reinforcement learning.
method Introduces elite policy gradients and a two-step merging method to balance bias-variance tradeoffs.
result Two-step merging outperforms interpolation merging and state-of-the-art algorithms on benchmark control tasks.
Deep RL policies share adversarial features across different MDPs.
problem Understanding decision boundaries and loss landscapes in neural policies.
method Investigating similarities in high sensitivity directions across MDPs using Arcade Learning Environment.
result High sensitivity directions for neural policies are correlated across MDPs, suggesting shared non-robust features.
PTF accelerates RL by reusing source policies without measuring task similarity.
problem Leveraging prior knowledge for faster RL.
method Adaptive Policy Transfer Framework (PTF) for RL.
result Significantly accelerates RL learning process and surpasses state-of-the-art methods.
Study on rapid policy changes in reinforcement learning.
problem Rapid change of greedy policy in reinforcement learning.
method Empirical study and ablation analysis.
result Policy churn is a beneficial form of implicit exploration.
This paper studies learning rate policies for deep neural networks, offering metrics and tools for better tuning.
problem Effective tuning of learning rates for deep neural networks is challenging and crucial for achieving high accuracy.
method Comprehensive study of 13 learning rate functions, proposing metrics for evaluation, and developing LRBench for benchmarking and selection.
result Identification of good learning rate policies with effective ranges and step sizes for various LR update schedules.
This work tackles risk-sensitive deep RL by optimizing policies with variance constraints.
problem Risk and aleatoric uncertainty in deep reinforcement learning.
method Lagrangian and Fenchel dualities to transform the problem into an unconstrained saddle-point policy optimization problem, and an actor-critic algorithm to iteratively update policy, Lagrange multiplier, and Fenchel dual variable.
result The proposed actor-critic algorithm finds a globally optimal policy at a sublinear rate.
Automated testing framework finds weaknesses in deep control policies.
problem Safety of deep neural network control policies is difficult to validate.
method Adversarial reinforcement learning to test and find weaknesses.
result Framework finds weaknesses not evident during manual testing.
New algorithm improves deep learning stability with limited data.
problem Stability and robustness in reinforcement learning with scarce data.
method Uncertainty-aware trust region approach to policy optimization.
result Stable policy updates adapt to uncertainty levels during learning.
Paper introduces DQPOPE for estimating return distributions in reinforcement learning.
problem Estimating the entire return distribution from off-policy data.
method Deep quantile process regression for distributional off-policy evaluation.
result DQPOPE achieves statistical advantages by estimating full return distribution with same sample size.
This paper uses deep reinforcement learning to optimize stock portfolios considering transaction costs and risks.
problem Optimizing stock portfolios with transaction costs and risks.
method Formulated stock portfolio optimization as a reinforcement learning problem, applied DDPG, GDPG, and PPO algorithms, and used Wavelet Transform.
result DDPG and GDPG algorithms outperformed PPO in continuous action space.
Deep active inference learns policies from sensory inputs.
problem Learning policies in partially observable domains.
method Optimizes expected free energy with a variational autoencoder.
result Comparable or better performance than deep Q-learning.
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
Paper benchmarks DRL policies' resilience to state transitions.
problem Measuring DRL policies' resilience to state perturbations.
method Disentangled representation learning and RL-based techniques.
result Demonstrated feasibility of resilience benchmarking in DQN, A2C, and PPO2.
This paper applies CPI to deep RL, improving stability and performance.
problem Improving stability and performance in deep reinforcement learning.
method Combines Conservative Policy Iteration with deep neural networks and adaptive mixture rates.
result Demonstrates improved stability and performance in deep RL algorithms.
Efficient deep policy gradient method for continuous-time control problems.
problem Optimal control in continuous time with fine time discretization.
method Multi-scale deep policy gradient method with varying time discretization.
result Targeted efficiency in computational resources achieved through multi-scale approach.
Stabilizes policy optimization with off-policy data using divergence augmentation.
problem Premature convergence and instability in policy optimization with off-policy data.
method Incorporates Bregman divergence between behavior and current policies to ensure safe policy updates.
result Empirically shows better performance in data-scarce scenarios compared to other algorithms.
This paper compares eight DRL algorithms for dynamic hedging.
problem Optimal dynamic hedging strategies using Deep Reinforcement Learning.
method Eight DRL algorithms (MCPG, PPO, DQL, DDPG) compared using a GJR-GARCH(1,1) simulated dataset.
result MCPG and PPO outperform the Black-Scholes delta hedge baseline.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Deep neural networks can estimate Q-values efficiently on low-dimensional state-action spaces.
problem Estimating the performance of a reinforcement learning policy using data from a different policy.
method Deep fitted Q-evaluation method leveraging manifold structure and convolutional neural networks.
result Sharp error bound for fitted Q-evaluation depends on intrinsic dimension and function space mismatch.
Accelerates deep RL algorithms with regularized Anderson acceleration.
problem Slow convergence and sample inefficiency in model-free, off-policy deep RL.
method Proposes a general acceleration method for deep RL by extending regularized Anderson acceleration.
result Improves both learning speed and final performance of deep RL algorithms.
Adaptive policies for multi-agent RL improve adaptiveness in changing environments.
problem Non-stationarity in multi-agent reinforcement learning where other agents may alter their policies.
method Train multiple adaptive policies for each agent and a policy predictor to select the best policy at execution time.
result Agents trained with our method outperform state-of-the-art methods in all tested environments.
Adversarial policies can defeat RL agents in multi-agent environments.
problem Vulnerability of RL policies to adversarial perturbations.
method Demonstrated adversarial policies in a multi-agent, high-dimensional environment.
result Adversarial policies reliably win against RL agents but generate seemingly random behavior.
Deep RL learns 2-opt heuristics to improve TSP solutions.
problem Improving TSP solutions beyond initial heuristics.
method Deep reinforcement learning to learn 2-opt operations.
result Learned policies improve solutions faster than previous methods.
Robust HVA adjusts deep hedging policies for market frictions and transaction costs.
problem Ensuring deep hedging policies are financially feasible under market frictions and transaction costs.
method Applying a robust hedging valuation adjustment (HVA) post-training to evaluate and adjust policies for funding and margin add-ons.
result A single HVA computation provides a consistent reserve for funding and margin, improving financial feasibility of deep hedging policies.
FiDi-RL combines deep RL with FiDi policy search for efficient continuous control.
problem Challenges in continuous control tasks using reinforcement learning.
method Combines Deep Deterministic Policy Gradients (DDPG) with Augment Random Search (ARS) using FiDi policy search.
result Improves data efficiency and stability of ARS.
Deep RL approach improves MIS for complex environments.
problem Improving off-policy evaluation for complex environments.
method Uses successor representation from deep RL to decouple reward and dynamics.
result Empirically stable and applicable to high-dimensional domains.
Paper optimizes traffic signal control for better traffic flow.
problem Optimizing traffic signal control to reduce congestion and improve safety.
method Value-based reinforcement learning with interpretable policy functions (polynomial functions).
result Deep Regulatable Hardmax Q-learning variant reduces vehicle delay by up to 19.4%.
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…
Enhances deep RL learning with stable policy updates.
problem Stability and performance degradation in deep RL methods.
method EVEREST method providing conservative updates with confidence bounds.
result Significant improvements in continuous control and Atari benchmarks.
New RL algorithms improve control tasks with data reuse.
problem Real-world control requires performance guarantees and data efficiency.
method Generalized Policy Improvement combining on-policy guarantees and sample reuse.
result Extensive experimental analysis shows benefits of new algorithms.
We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then con…
Deep learning analyzes healthcare provider actions and patient outcomes.
problem Understanding provider behavior in non-randomized healthcare settings.
method Deep causal behavioral policy learning (DC-BPL) using transformer architecture.
result Optimal provider policies identified for specific patient types.
NPMD uses CNNs to optimize policies on low-dimensional manifolds, reducing sample complexity.
problem Explaining the effectiveness of deep policy gradient methods in high-dimensional RL.
method Neural policy mirror descent (NPMD) with CNNs, considering state spaces as low-dimensional manifolds.
result NPMD finds ε-optimal policies with O(ε^(-d/α-2)) samples, leveraging low-dimensional structure.
Regularization improves policy optimization in RL, especially on harder tasks.
problem Lack of conventional regularization in RL methods.
method Comprehensive study of regularization techniques on policy networks with multiple RL algorithms.
result Conventional regularization techniques significantly improve policy optimization, especially on harder tasks.
Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly …
A new method improves policy evaluation in RL by tracking value uncertainties.
problem Limitations in existing policy evaluation methods for deep RL tasks.
method KOVA (Kalman Optimization for Value Approximation) based on extended Kalman filter.
result KOVA minimizes a regularized objective function that considers parameter and noisy return uncertainties.