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.
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.
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.
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.
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.
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.
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.
New RL method handles diverse human operator data.
problem Handling data from multiple, unknown policies.
method Domain-Invariant Model-based Offline RL (DIMORL) with Risk Extrapolation (REx).
result Models trained with REx generalize better across different demonstrators.
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.
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.
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.
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.
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.
This paper combines LLMs with RL for better trading strategies.
problem Myopic behavior and opaque policies in RL for trading.
method LLMs generate strategic trading advice to guide RL agents.
result LLM-guided RL agents outperform unguided RL in return and risk metrics.
New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.
problem Achieving strong performance guarantees in reinforcement learning.
method Proposes algorithms for nonlinear bandits and model-based episodic RL with a bounded eluder dimension.
result Achieves uniform-PAC sample complexity that matches state-of-the-art regret bounds or sample complexity guarantees.
A new framework reduces RL sample complexity for complex MDPs.
problem Handling large state and action spaces in reinforcement learning.
method Unified model-based and model-free RL framework with ABC class, novel estimation function, and functional eluder dimension.
result OPERA algorithm achieves sample-efficient regret bounds for various MDP models.
Swift Hydra uses RL and generative AI to improve anomaly detection.
problem Generalization to unseen anomalies in critical systems.
method Generative AI and reinforcement learning (RL) for synthesizing diverse anomaly samples.
result Swift Hydra outperforms state-of-the-art models on ADBench benchmark.
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 paper, a novel experienced deep reinforcement learning (deep-RL) framework is proposed to provide model-free resource allocation for ultra reliable low latency communication (URLLC). The proposed, experienced deep-RL framework can guarantee high end-to-end reliability and low end-to-end latency, under explicit …
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
problem Limited graph reasoning abilities of LLMs, especially in synthetic graph-theoretic tasks.
method Curated synthetic graph dataset, RL training on LLMs.
result Significant improvements in graph reasoning, zero-shot generalization to unseen tasks.
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.
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
problem Challenging in sequence generation tasks to generate sequences with specific desired goals.
method Integrates GAN and RL to optimize desired goal scores using policy gradients.
result Achieves higher desired scores in text and real-valued sequence generation.
Paper develops efficient RL algorithm for general value function approximation.
problem Lack of theory for RL with general value function approximation.
method Provable efficient RL algorithm using bounded eluder dimension.
result Achieves a regret bound of O ~ ( p o l y ( d H ) T ) \widetilde{O}(\mathrm{poly}(dH)\sqrt{T}) O ( poly ( d H ) T ) . Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architec…
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.
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.
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.
We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic model class and analyze their statistical properties. Our algorithms have sample …
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.
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.
RL agents learn from a few tasks to generalize to new ones.
problem Creating efficient RL agents that can solve multiple tasks.
method GHP-MDPs model with latent variables for hidden parameters.
result State-of-the-art performance and sample-efficiency on new tasks.
In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text conversion, and image caption generation. The underlying framework for all these…
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.
Maximize to Explore integrates RL components for efficient policy discovery.
problem Balancing exploration and exploitation in online RL with general function approximators.
method Integrates estimation, planning, and exploration into a single objective function.
result Achieves sublinear regret for MDPs and MGs with general function approximations.
This work bridges offline RL and DRL to address distributional shift.
problem Distributional shift in offline RL due to difference in state-action visitation distributions.
method Proposes offline RL algorithms using DRL framework, characterizes sample complexity under single policy concentrability.
result Demonstrates superior performance of proposed algorithms through simulations.
In unsupervised data generation tasks, besides the generation of a sample based on previous observations, one would often like to give hints to the model in order to bias the generation towards desirable metrics. We propose a method that combines Generative Adversarial Networks (GANs) and reinforcement learning (RL) in…
Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to di…
Pre-trained LLM adapted with LoRA improves offline RL for quantitative trading.
problem Challenges in offline RL for quantitative trading due to complex temporal dependencies and overfitting.
method Integrates pre-trained GPT-2 weights and LoRA for efficient fine-tuning of a Decision Transformer.
result Outperforms existing offline RL methods in certain trading scenarios.
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.
Improved RL model for fragment-based molecule generation.
problem Generating molecules with high docking scores.
method Thorough reproduction, scrutiny, and improvement of the FREED model.
result The improved model produces molecules with superior docking scores.
The smallest eigenvectors of the graph Laplacian are well-known to provide a succinct representation of the geometry of a weighted graph. In reinforcement learning (RL), where the weighted graph may be interpreted as the state transition process induced by a behavior policy acting on the environment, approximating the …
State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered experience. In this paper, we focus on model-based RL in the finite-state finite-horizon…
MiniHack simplifies creation of complex RL environments.
problem Limited availability of challenging RL benchmarks.
method Develops a sandbox framework for easy RL environment design.
result MiniHack enables rapid creation of diverse RL testbeds.
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. We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimiz…
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.
Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.
problem Performance saturation in RL algorithms for LLMs.
method Entrocraft uses rejection sampling to bias advantage distributions for customized entropy schedules.
result Entrocraft significantly improves generalization, output diversity, and long-term training in 4B models.