This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
MOReL learns offline RL policies using pessimistic MDPs.
problem Offline RL's data efficiency and velocity.
method Two-step process: learn P-MDP and near-optimal policy in it.
result MOReL is minimax optimal and matches state-of-the-art results.
Paper shows RLHF can be solved similarly to standard RL.
problem Difficulty of RLHF compared to standard RL.
method Reduction to reward-based RL techniques.
result RLHF can be solved using existing algorithms for reward-based RL.
M3PO improves model-based meta-RL with theoretical guarantees.
problem Improving sample efficiency in multi-task RL with theoretical guarantees.
method Extending Janner et al. (2019) theorems, proposing M3PO with performance guarantees.
result M3PO outperforms existing methods in continuous-control benchmarks.
RL tackles decision making in unknown environments, focusing on efficiency and efficacy.
problem Efficiency and efficacy in RL algorithms for sample-starved situations.
method Markov Decision Processes, model-based and value-based approaches, policy optimization.
result Enhanced understanding and improvements in sample and computational efficacies of RL algorithms.
Generative flow networks use RL to learn probabilistic models efficiently.
problem Training generative models with RL for compositional discrete objects.
method Reformulate GFlowNet training as entropy-regularized RL with specific reward and regularizer.
result Entropy-regularized RL can be competitive with established GFlowNet training methods.
RL applied to finance tasks, highlighting challenges and future directions.
problem Decision-making tasks in finance using RL.
method Meta-analysis of RL applications, identifying challenges and proposing future directions.
result Challenges in RL performance and future research directions.
Optimistic RL algorithms are simplified for deep RL with competitive performance.
problem Achieving accurate optimism in model-based RL for large-scale problems.
method Interpreting scalable optimistic model-based algorithms as solving a tractable noise augmented MDP.
result Competitive regret bound of i l d e O ( ∣ S ∣ H ∣ A ∣ T ) ilde{\mathcal{O}}( |\mathcal{S}|H\sqrt{|\mathcal{A}| T } ) i l d e O ( ∣ S ∣ H ∣ A ∣ T ) for Gaussian noise augmentation. This study explains RL training dynamics in LLMs, focusing on token-level optimization and reasoning pattern reshaping.
problem Understanding the training dynamics of RL in LLMs to improve their reasoning capabilities.
method Empirical analysis and theoretical modeling of RL training process, focusing on reasoning patterns and token optimization.
result RL primarily optimizes a sparse subset of critical tokens, reshaping reasoning pattern distributions and affecting model performance.
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.
Surrogate models speed up RL training in dynamic systems.
problem High computational cost of high-fidelity simulations.
method Developed and tested surrogate models for RL training.
result Surrogate models can significantly accelerate RL training.
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
PriMORL trains private RL policies on offline data.
problem Private reinforcement learning on offline data.
method PriMORL learns DP models of the environment and optimizes a policy on the penalized private model.
result PriMORL enables training of private RL agents on complex tasks.
RH-UCRL combines pessimism and optimism for robust RL.
problem Ensuring reliable performance in real-world RL tasks with worst-case scenarios.
method RH-UCRL is a model-based RL algorithm that optimizes between an agent and an adversary, distinguishing between epistemic and aleatoric uncertainty.
result RH-UCRL achieves near-optimal sample complexity guarantees and outperforms other robust RL algorithms in adversarial environments.
FOCUS improves offline RL by incorporating causal structure into world-models.
problem Learning effective policies from historical data without interaction.
method FOCUS proposes a practical algorithm that learns and leverages causal structure in offline RL.
result FOCUS outperforms plain model-based offline RL algorithms and other causal model-based RL algorithms.
New RL algorithm minimizes distributional learning error.
problem Improving distributional reinforcement learning for better error minimization.
method Proposes a new model-based algorithm with theoretical minimax optimality.
result Proves minimax optimality for approximating return distributions.
This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action selection. Therefore, computa…
Catalyst.RL accelerates RL research with efficient training.
problem Efficient reinforcement learning training in complex environments.
method Open-source PyTorch framework with distributed training and RL algorithms.
result Catalyst.RL achieved 2nd place in a computationally expensive RL challenge.
RL agents outperform baselines in asset allocation.
problem Optimizing asset allocation using reinforcement learning.
method Model-free deep RL agents trained on real-world stock prices.
result RL agents significantly outperformed random and uniform allocation.
Mixed RL improves RL efficiency with dual representations.
problem Poor sampling efficiency in RL methods.
method Uses dual representations of environmental dynamics to search optimal policies.
result Proves convergence and recursive stability of the mixed RL.
Unified framework for model-based RL with sample complexity guarantees.
problem Designing efficient posterior sampling methods for model-based RL.
method Optimistic posterior sampling, Hellinger distance reduction, data likelihood measurement.
result Unified algorithms with state-of-the-art sample complexity guarantees.
This paper compares expected and distributional reinforcement learning methods.
problem Understanding why distributional reinforcement learning performs better than expected reinforcement learning.
method Analyzes differences in tabular, linear, and non-linear approximation settings.
result Distributional RL can hurt performance if it does not induce identical behavior.
catalyst.RL simplifies RL research, enabling reproducibility and efficiency.
problem Difficulty in reproducing and comparing RL algorithms.
method Open-source framework with distributed training, flexible configurations, and efficient RL algorithms.
result Demonstrated effectiveness on AI for Prosthetics Challenge, achieving 3rd place.
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.
Deep RL model optimizes dynamic portfolio allocation.
problem Automating dynamic portfolio optimization with machine learning.
method Model-based deep reinforcement learning with prediction, data augmentation, and behavior cloning modules.
result Robust, profitable, and risk-sensitive trading strategy compared to baselines.
Deep-RLS uses deep learning to improve PCA for better source separation.
problem Improving PCA for better source separation in nonlinear systems.
method Inspired by RLS, Deep-RLS unfolds RLS iterations into a deep neural network.
result Deep-RLS significantly improves accuracy in recovering source signals.
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.
Survey of RL algorithms for dynamic environments.
problem Handling changing operating conditions in RL.
method Survey of algorithms developed for non-stationary environments.
result Methods to adapt to varying operating conditions.
New model-free DR-RL algorithm with finite sample complexity.
problem Limited model-free DR-RL methods with convergence guarantees or sample complexities.
method Integrates Multi-level Monte Carlo (MLMC) technique with threshold mechanism.
result First model-free DR-RL approach with finite sample complexity for total variation and Chi-square divergence.
Adapts Floyd-Warshall algorithm for RL to improve multi-goal task learning.
problem Limited transfer of learned information in model-free RL for dynamic goal tasks.
method Adapts Floyd-Warshall algorithm for RL to learn goal-conditioned action-value functions.
result FWRL achieves higher reward strategies in multi-goal tasks with fewer samples.
Paper uses RL for better credit scoring and underwriting.
problem Traditional underwriting methods are ungeneralizable in complex scenarios.
method Adapts RL principles for credit scoring, incorporating action space renewal and multi-choice actions.
result RL-based algorithms outperform traditional methods in aligned data scenarios.
MVFST-RL tackles real-time network congestion control with RL.
problem Real-time network congestion control with RL in asynchronous environments.
method Asynchronous RL framework for delayed actions in QUIC.
result Scalable framework for congestion control in QUIC with improved state-of-the-art RL.
Safe RL-based vibration control using LQR guidance.
problem Training risks in RL-based vibration control.
method Hybrid control framework combining LQR and RL.
result LQR controller outperforms uncontrolled scenario.
RL agent outperforms model-based approach in detecting price manipulation.
problem Detecting and exploiting price manipulation opportunities.
method Compared model-free RL with model-based approach in a market with Almgren-Chriss framework.
result RL consistently outperforms model-based approach, especially with noisy parameter estimates.
HTMRL uses HTM for RL, adapting faster to changing environments.
problem Adapting to non-stationary environments in RL.
method Strictly HTM-based RL algorithm.
result HTMRL adapts faster to changing environments in a 10-armed bandit.
Deep RL strategy improves natural gas trading performance.
problem Improving natural gas trading performance using Deep RL.
method Domain-adapted Deep RL for natural gas futures trading.
result Deep RL strategy outperforms benchmarks and reduces transaction costs.
Greedy policies in model-based RL achieve tight regret bounds without full planning.
problem Achieving efficient RL algorithms in MDP settings.
method Using greedy policies for 1-step planning in model-based RL.
result Greedy policies achieve i l d e O ( H S A T ) ilde{\mathcal{O}}(\sqrt{HSAT}) i l d e O ( H S A T ) regret bounds. LaPSRL achieves optimal regret for isoperimetric RL distributions.
problem Designing RL algorithms with sublinear regret for non-log-concave distributions.
method Posterior Sampling (PSRL) and Langevin sampling (LaPSRL) for isoperimetric distributions.
result LaPSRL achieves order-optimal regret and subquadratic complexity.
Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
New RL algorithm tackles online robust MDPs with uncertainty.
problem Developing robust reinforcement learning models for real-world environments.
method Proposes a robust optimistic policy optimization algorithm for online robust MDPs.
result Establishes the first regret bound for online robust MDPs.
Paper proposes a hybrid RL algorithm that combines offline and online data without needing reward info.
problem How to efficiently use online data to improve RL policies using only offline data.
method A three-stage hybrid RL algorithm that uses reward-agnostic exploration and model-based offline RL.
result The hybrid RL algorithm outperforms both pure offline and pure online RL in sample complexity.
Modular RL modules solve complex 3D Sokoban tasks.
problem Solving complex, integrated tasks combining visual, physical, and abstract reasoning.
method Compose RL modules in a sense-plan-act hierarchy, using only model-free methods.
result Modular RL outperforms state-of-the-art monolithic RL on Mujoban.
This tutorial reviews RL-based methods for optimizing diffusion models to maximize specific metrics.
problem Optimizing diffusion models to generate samples that maximize specific metrics in practical applications.
method Various RL algorithms including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
result Exploration of strengths and limitations of RL-based fine-tuning algorithms and their benefits compared to non-RL-based approaches.
Myopic optimization outperforms reinforcement learning in portfolio management, leading to lower returns and higher risks.
problem Reinforcement learning strategies in portfolio management yield lower or negative returns and higher risks compared to myopic optimization.
method Modeling execution/liquidation frictions with mark-to-market accounting, using Malliavin calculus to derive policy gradients and risk shadow price, and quantifying phantom profit.
result Myopic optimization outperforms reinforcement learning in portfolio management, leading to better returns and lower risks.
Interactive tool helps RL researchers debug and understand their models.
problem Challenges in debugging reinforcement learning algorithms.
method Design and implementation of an interactive visualization tool.
result Addresses features missing from previous tools for RL.
Direct and indirect RL methods classified and compared.
problem Classifying RL methods for sequential decision making.
method Direct RL solves optimal policy directly, indirect RL solves Bellman equation.
result Direct and indirect RL methods are equivalent and can be unified.
Mid-training improves RL by identifying compact action abstractions.
problem Unlocking full potential of RL with large language models.
method RA3 algorithm that optimizes sequential variational lower bound and discovers latent structures via RL.
result Improves performance by 8 points on HumanEval and 4 points on MBPP.
Overview of deep reinforcement learning, including elements and applications.
problem Optimizing decision-making in complex environments.
method Combining deep learning with reinforcement learning algorithms.
result Effective in diverse applications like games, robotics, and NLP.