PDCA algorithm learns policies for RL with constraints using a primal-dual approach.
problem Offline constrained reinforcement learning with general function approximation.
method Primal-Dual-Critic Algorithm (PDCA) using a primal-dual approach.
result PDCA finds a near saddle point of the Lagrangian, nearly optimal for constrained RL.
State-constrained offline RL expands RL's learning scope.
problem Batch-constrained offline RL limits policies to seen actions.
method Introduces state-constrained offline RL focusing on state distribution.
result Policy can take high-quality out-of-distribution actions.
FMDP-BF algorithm improves RL in factored MDPs with exponential regret reduction.
problem Efficient reinforcement learning in factored MDPs with constrained RL.
method FMDP-BF algorithm leveraging factorization structure of FMDPs.
result FMDP-BF's regret is exponentially smaller than optimal algorithms for non-factored MDPs.
Offline RL tackles resource-constrained online deployment with improved policy transfer.
problem Training policies with limited online features using a rich offline dataset.
method Introduce a policy transfer algorithm that first trains a teacher agent with full offline features and then transfers knowledge to a student agent with limited online features.
result Consistent improvement in performance over baseline methods on resource-constrained datasets.
Study examines sample complexity for RL with safety constraints.
problem Ensuring safety in RL for systems with constraints.
method Analyzes two RL approaches: generative and online.
result Sample complexity increased by a logarithmic factor in constraints.
Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.
problem Unexplainable behaviours and lack of safety guarantees in RL for real vehicles.
method PCPO framework with trust regions and parallel learners.
result Safe learning confirmed for autonomous vehicles with fast convergence.
Paper characterizes optimal language model alignment methods.
problem Aligning language models to maximize reward while keeping them close to the original model.
method KL-constrained reinforcement learning and best-of-N methods.
result Optimal KL-constrained RL solution has a large deviation principle rate function.
Meta-gradient D4PG optimizes performance and constraint adherence in RL.
problem Balancing performance and adherence to complex constraints in RL.
method Uses meta-gradients to find a balance between expected return and minimizing constraint violations.
result Meta-gradient D4PG consistently outperforms baselines across MuJoCo domains.
VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.
problem Optimizing VaR-constrained reinforcement learning problems.
method Combines Cantelli's inequality and trust-region framework for efficient and conservative optimization.
result Achieves zero constraint violations during training in feasible environments.
A new RL method handles uncertainty and constraints in real-time optimization.
problem Real-time optimization under process uncertainty and constraints.
method Chance-constrained reinforcement learning to handle probabilistic state constraints.
result Satisfies process constraints with high probability in real-time.
Paper uses RL to solve constrained combinatorial optimization problems.
problem Constrained combinatorial optimization problems.
method Extending NCO theory to CMDPs, using RL with penalty signals.
result Proposes a superior method for solving constrained problems.
In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum degree that is the same at each state. This can cause batch RL to be overly conservat…
Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.
problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.
KCRL learns stable policies for nonlinear systems with formal guarantees.
problem Lack of stabilization guarantees in RL methods for safety-critical systems.
method KCRL uses Krasovskii's Lyapunov functions as a stability constraint and a primal-dual approach to learn stabilizing policies.
result KCRL guarantees learning a stabilizing policy in a finite number of interactions.
Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this paper, we draw connections between DP and (constrained) convex optimization. Specifically, we show clear links in the algorithmic structure b…
New RL approach tackles constrained Markov decision processes.
problem Applying RL to physical systems with safety constraints.
method Formulated as a Constrained Markov Decision Process (CMDP), introduced a safe policy improvement method.
result Agent learns to maximize returns while satisfying constraints.
Improved RL algorithm with linear MDPs for offline learning with partial data coverage.
problem Efficient offline RL with linear MDPs under partial data coverage.
method Primal-dual algorithm with O(ε−2) sample complexity. result First computationally efficient algorithm with O(ε−2) sample complexity for offline RL with linear MDPs under partial data coverage. Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the Q-value from finite past experience data. Greedy policies or even …
A simple approach to offline RL without additional complexity.
problem Learning from a fixed dataset of actions with value estimation errors.
method Adding a behavior cloning term to the policy update of an online RL algorithm and normalizing the data.
result Matches the performance of state-of-the-art offline RL algorithms with minimal changes.
In this work, we introduce Graph Pointer Networks (GPNs) trained using reinforcement learning (RL) for tackling the traveling salesman problem (TSP). GPNs build upon Pointer Networks by introducing a graph embedding layer on the input, which captures relationships between nodes. Furthermore, to approximate solutions to…
evo-RL combines evolutionary computation with reinforcement learning for better adaptability.
problem Improving reinforcement learning algorithms' adaptability and performance in environments with rewardless states.
method Embedding reinforcement learning in an evolutionary cycle, distinguishing instinctive from learnable behavior.
result evo-RL leads to state-of-the-art performance on OpenAI Gym control problems with rewardless states.
Survey of mathematical foundations for reinforcement learning.
problem Design and analysis of modern reinforcement learning algorithms.
method Organizes mathematical structures from probability, optimization, and operator theory.
result Unified mathematical entry point for researchers in various fields.
New RL algorithm learns good actions from offline data, reducing uncertainty and divergence.
problem Limited applicability of current RL algorithms in real-world settings due to high costs of exploration.
method Proposes an algorithm for batch RL using a fixed offline dataset, with penalties for policy and value constraints.
result Compared favorably to state-of-the-art methods on 32 continuous-action benchmarks.
Study proposes adaptive RL for dynamic portfolio optimization.
problem Traditional portfolio optimization models fail to adapt to regime shifts.
method Regime-aware reinforcement learning framework with hybrid observations and constrained reward functions.
result Transformer PPO achieves highest risk-adjusted returns, while LSTM variants offer a good balance.
In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …
Develops ODRPO to improve RL algorithms with better performance and stability.
problem RL algorithms converge to sub-optimal solutions due to limited policy representation.
method Integrates DRO approach to solve trust region constrained optimization problem without parameterizing policies.
result Achieves globally optimal policy update and higher sample efficiency.
Choquet regularization improves exploration in RL.
problem Improving exploration in reinforcement learning.
method Introducing Choquet regularizers to measure and manage exploration, reformulating RL problems and deriving explicit solutions.
result Explicit optimal distributions and Choquet regularizers for various exploratory samplers.
Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations.…
This paper shows RL with KL penalties is equivalent to Bayesian inference for fine-tuning LMs.
problem Fine-tuning large language models to avoid undesirable features.
method Analyzed KL-regularized RL and showed it's equivalent to variational inference.
result KL-regularized RL avoids distribution collapse and is more insightful as Bayesian inference.
The paper tackles safe reinforcement learning with convex regularization.
problem Safe reinforcement learning in complex, high-dimensional settings with safety constraints.
method Doubly-regularized RL framework combining reward and parameter regularization, formulated as a convex regularized objective with parametrized policies on an infinite-dimensional statistical manifold.
result Exponential convergence guarantees under sufficient regularization, robust theoretical insights and guarantees for safe RL.
One-step policy improvement outperforms iterative RL methods on D4RL.
problem Improving offline RL without off-policy evaluation.
method One-step constrained/regularized policy improvement using on-policy Q estimates.
result One-step algorithm outperforms iterative algorithms on D4RL benchmark.
Revel tackles safe exploration in RL with verified symbolic policies.
problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.
Enhances RL by controlling policy stochasticity through trajectory entropy constraints.
problem Non-stationary Q-value estimation and short-sighted entropy tuning in maximum entropy RL.
method Proposes TECRL framework with separate Q-functions for reward and entropy, enforcing a trajectory entropy constraint.
result DSAC-E algorithm achieves higher returns and better stability on OpenAI Gym benchmarks.
MOPO optimizes offline RL by penalizing dynamics uncertainty.
problem Learning policies from offline data with distributional shift.
method Modify model-based RL to avoid distributional shift.
result MOPO outperforms model-free and standard model-based RL.
New algorithm reduces sample complexity for safe reinforcement learning.
problem Safe reinforcement learning in constrained MDPs with performance and safety constraints.
method Model-based primal-dual algorithm balancing regret and bounded constraint violations.
result Proves near-optimal policies with bounded violations or zero violations in CMDPs.
KL-constrained API shows optimization issues and improved with regularization.
problem Optimization issues in KL-constrained API algorithms.
method Comparison of KL divergence as a constraint vs. regularizer, empirical evaluation.
result KL-constrained API is not guaranteed to converge and incurs linear regret.
New RL algorithm ensures stable, replicable policies.
problem Stability and replicability issues in RL algorithms.
method Introduced weak and strong forms of list replicability, developed a novel planning strategy, and tested state reachability.
result Proved efficient tabular RL algorithm with polynomial list complexity.
Mirror descent method improved RL algorithms.
problem Improving RL algorithms for better performance.
method Mirror descent method applied to RL, solving trust-region problems.
result MDPO outperforms or matches other RL algorithms in continuous control tasks.
Simplifies BCQ to match and outperform state-of-the-art in offline RL benchmarks.
problem Sample efficiency in offline reinforcement learning.
method Introduces EMaQ, a novel backup operator for offline RL.
result EMaQ matches and outperforms prior state-of-the-art in offline RL benchmarks.
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…
New RL approach optimizes resource allocation in multiservice networks.
problem Optimizing resource allocation in multiservice wireless systems with QoS constraints.
method Distributed deep reinforcement learning for non-convex optimization.
result Near optimal performance in terms of throughput and outage rate.
Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks. However, the majority of autonomous RL algorithms require a large number of interactions with the environment. A large number of interactions may be impractical in many real…
AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.
problem Memory overhead and hyperparameter complexity in adaptive optimizers.
method Tensor-wise L2 normalization followed by a smooth hyperbolic tangent transformation controlled by a single parameter.
result AlphaGrad provides enhanced training stability and competitive performance in various RL algorithms.
Study uses RL to optimize investment with financial constraints, showing exploration benefits.
problem Optimal investment with financial constraints in continuous time.
method Reinforcement learning framework, focusing on Gaussian and truncated Gaussian distributions.
result Exploration leads to more dispersed wealth distribution with heavier tails, especially with smaller exploration parameters.
Recently, Reinforcement Learning (RL) approaches have demonstrated advanced performance in image captioning by directly optimizing the metric used for testing. However, this shaped reward introduces learning biases, which reduces the readability of generated text. In addition, the large sample space makes training unst…