Algorithm learns optimal dynamic mechanisms from data.
problem Designing optimal mechanisms for dynamic settings with unknown reward functions.
method Offline reinforcement learning with pessimism principle.
result Learned mechanisms are efficient, individually rational, and truthful.
New RL approach learns dynamic VCG mechanisms in unknown MDP environments.
problem Learning dynamic VCG mechanisms in unknown MDP environments.
method Reward-free online RL for exploration, combined with function approximation.
result Regret bound of O~(T2/3) for dynamic VCG mechanism learning. Novel RL approach for molecular design using quantum mechanics.
problem Existing RL methods for molecular design are limited in scope and reward function.
method Formulation in Cartesian coordinates, direct use of quantum mechanics for reward function, translation and rotation invariant state-action space.
result Agent efficiently learns to solve molecular design tasks from scratch.
Optimizes impression allocation for e-commerce platforms using reinforcement learning.
problem Short-term and long-term returns are not optimized in current e-commerce platform allocation mechanisms.
method Formal lifecycle model of products, reinforcement learning framework, first principal component based permutation, novel experiences generation method.
result Significant improvement in platform and participant health with optimized impression allocation.
Generative thermal design learns optimal shapes using multi-agent reinforcement learning.
problem Complex thermal design challenges due to convection-diffusion equation and boundary interactions.
method Cooperative multi-agent deep reinforcement learning with continuous geometric representation.
result Framework learns optimal design strategies without shape derivation or differentiable objectives.
We use Bayesian optimal experimental design to generate near-optimal attention sequences for faster hard attention training.
problem Training hard attention mechanisms is computationally expensive and high-variance.
method We frame hard attention as a BOED problem and use approximation methods from BOED to generate near-optimal attention sequences.
result Near-optimal attention sequences can speed up hard attention training and be reused by other networks.
Framework improves self-play for cooperative multi-agent learning.
problem Evolutionary learning converges to bad local optima in multi-agent RL.
method Add imaginary rewards using peer prediction method to elicit truthful signals.
result State-of-the-art performance in predator prey, traffic junction and StarCraft tasks.
MFRL-BI controls manufacturing processes without needing accurate models.
problem Model inaccuracies in complex manufacturing systems.
method Model-free reinforcement learning with Bayesian inference.
result Demonstrated to perform well in a nonlinear CMP process.
ASLA learns atomic structures using neural networks and reinforcement learning.
problem Designing materials and drugs with desired properties.
method Atomistic structure learning algorithm (ASLA) using a convolutional neural network and reinforcement learning.
result ASLA can predict optimal structural arrangements of atoms for various target properties.
This research tackles information design in multi-agent reinforcement learning.
problem Designing information to influence other adaptive agents in a non-stationary environment.
method Formulated Markov signaling game, introduced signaling gradient and extended obedience constraints.
result Developed efficient algorithm for mixed-motive tasks in multi-agent reinforcement learning.
Deep RL solves global routing problems more efficiently.
problem Challenging problem in electronic circuit design and other systems.
method Deep reinforcement learning for conjoint optimization.
result Deep RL outperforms A* method in routing solutions.
A novel framework for adaptive multi-agent communication in reinforcement learning.
problem Manual specification of communication structures in multi-agent reinforcement learning.
method Learning Structured Communication (LSC) framework using hierarchical graph neural networks.
result Adaptive hierarchical formations and efficient message propagation among agents.
Automated theorem proving without imitation, using tf-idf for premise selection.
problem Automated theorem proving in large knowledge bases without human guidance.
method Exploration mechanism mixing tf-idf selected premises in a deep reinforcement learning context.
result The prover trained with this approach outperforms provers trained only on human proofs.
New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.
problem Domain-specific, compute-resource-maximizing, and non-reproducible participant solutions in reinforcement learning competitions.
method Submission retraining, domain randomization, desemantization through domain obfuscation, and compute/environment-sample budget limitation.
result Participant submissions are reproducible, non-specific to the competition environment, and sample/resource efficient.
Hybrid approach improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Approximate model from Model-Free RL, use Mean First Passage Times for reachability, design new algorithms.
result Hybrid approaches converge with fewer iterations and samples.
RAM extends attention-based mechanism for existence determination.
problem Binary determination of object existence in cluttered images.
method Recurrent attention model (RAM) with k-maximum aggregation layer and new reward mechanism. result Significant efficiency and accuracy improvement over existing approaches.
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.
Generative model solves financial market equilibria with stable reinforcement learning.
problem Financial market equilibria under realistic frictions and multiple agents.
method Generative adversarial reinforcement learning with decoupling feedback.
result Algorithm learns and predicts asset returns and volatilities.
Deep Sets improve reinforcement learning agent's object-centered navigation and generalization.
problem Improving reinforcement learning agents' ability to generalize to unseen objects and goals.
method Combining object-wise permutation invariant networks (Deep Sets) and gated-attention mechanisms.
result Agent demonstrates strong generalization to out-of-distribution goals in a procedurally-generated 2D world.
Improved risk-sensitive RL with exponential Bellman equation and better regret bounds.
problem Exponential gap between upper and lower bounds in risk-sensitive RL.
method Identified and addressed deficiencies in existing algorithms and analysis; developed novel analysis and exploration mechanism.
result Improved regret upper bounds over existing ones.
Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is one of the mechanisms proposed to mitigate adversarial examples---to address it…
This paper uses DRL for long-short portfolio optimization, improving risk-adjusted returns.
problem Traditional portfolio optimization limits diversification by excluding short-selling.
method Developed a DRL framework with a short-selling mechanism for continuous trading.
result DRL model with short-selling achieves superior risk-adjusted returns.
This paper uses deep RL to optimize market quotes from LOB data.
problem Optimizing quotes for market making from complex LOB data.
method Attn-LOB neural network with convolutional filters and attention mechanism for feature extraction; hybrid reward function for continuous action space.
result The RL agent outperforms traditional methods in market making tasks.
Meta-learning curiosity algorithms improves exploration across various tasks.
problem Generating curious behavior in reinforcement learning.
method Meta-learning approach to adapt reward signals dynamically.
result Two novel curiosity algorithms outperform human-designed ones.
JAX-LOB simulates thousands of LOBs for RL training.
problem Efficient simulation of large LOBs for RL training.
method GPU-accelerated JAX implementation of LOB simulator.
result JAX-LOB processes thousands of LOBs in parallel with reduced processing time.
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous …
New algorithm for multi-agent reinforcement learning with attention mechanism.
problem Challenges in training decentralized policies in multi-agent settings.
method Actor-attention-critic algorithm with centrally computed critics and attention mechanism.
result More effective and scalable learning in complex multi-agent environments.
A robot learns to classify images with limited perception using a layered reinforcement learning approach.
problem Image classification for robots with partial perception.
method Three-layer architecture using deep reinforcement learning, including meta-layer, action-layer, and classification-layer.
result The method achieves high accuracy on the MNIST dataset and provides explainability of the agent's decision-making process.
A new method transcribes complex structured images like musical scores.
problem Transcribing content from images with complex internal structure.
method Hierarchical Spotlight Transcribing Network (STN) framework with two-stage approach.
result Demonstrated effectiveness through experiments on various structural image datasets.
Deep Q-Learning system for straddle options in volatile markets.
problem High computational costs and unstable performance in high-volatility markets.
method Attention mechanisms in Transformer-DDQN, novel reward function, and resistance level identification.
result Transformer-DDQN model exhibits lowest maximum drawdown and highest average return.
Develops a method to define admissible rewards for robust policy evaluation in RL.
problem Defining a reward function for robust off-policy evaluation in RL with limited data.
method Identifies an admissible set of reward functions ensuring policies are close to past behavior and can be evaluated with high confidence.
result Demonstrates the approach on synthetic and real-world domains, including a critical care application.
CB-RL solves complex decision-making problems with contextual information and exogenous events.
problem Optimal policy in strategic decision-making problems that depend on environmental configuration and exogenous events.
method Contextual Bilevel Reinforcement Learning (CB-RL) with a stochastic Hyper Policy Gradient Descent (HPGD) algorithm.
result Demonstrated convergence and performance of the HPGD algorithm for reward shaping and tax design.
Combining visual attention with deep reinforcement learning improves sample efficiency.
problem Improving sample efficiency in deep reinforcement learning.
method Visual selective attention mechanism implemented using optical flow and batch normalization.
result Visual selective attention leads to improvements in sample efficiency on Atari games.
Taxonomy of knowledge modalities in RL for better transfer.
problem Tackling the transfer of knowledge in reinforcement learning.
method Systematic analysis of knowledge modalities in RL.
result A taxonomy of knowledge modalities in reinforcement learning.
We accelerate PMD algorithms for reinforcement learning using functional methods.
problem Improving reinforcement learning algorithms for large-scale optimization.
method Proposed a momentum-based update for PMD algorithms leveraging duality.
result The proposed method accelerates reinforcement learning algorithms.
Proposes hybrid reinforcement learning for both discrete and continuous control problems.
problem Real-world control problems involving both discrete and continuous decision variables.
method Solves hybrid problems by optimizing for discrete and continuous actions simultaneously.
result Efficiently solves hybrid reinforcement learning problems and improves upon expert heuristics.
Wield simplifies reinforcement learning task design.
problem Lack of suitable task representations for reinforcement learning.
method Introduces Wield, a system with software primitives and staged randomization protocol.
result Facilitates practical reinforcement learning through decoupling system and task design.
Proposes a method to improve reinforcement learning in multi-view environments.
problem Improving policy learning in environments with partial observability.
method Actor-Critic-Attention Mechanism for generating a single feature representation from multiple views.
result Our method outperforms state-of-the-art baselines on various complex 3D environments.
vsOED optimizes experiment design with reinforcement learning for Bayesian models.
problem Optimizing the sequence of experiments in Bayesian models for efficient data collection.
method Reinforcement learning with variational posterior approximations to optimize design policy.
result vsOED achieves superior sample efficiency compared to existing methods.
Study evaluates reinforcement learning algorithms for sequential experimental design.
problem Lack of generalization in reinforcement learning for experimental design.
method Investigated several reinforcement learning algorithms for sequential experimental design.
result Certain algorithms, using dropout or ensemble approaches, show attractive generalization properties.
Reinforcement learning improves game level design.
problem Creating high-quality game levels with limited examples.
method Transforming level design into a Markov decision process and training with reinforcement learning.
result Trained reinforcement learning agents can generate high-quality levels quickly.
A new reinforcement learning approach using competitive primitives that specialize and specialize based on information needs.
problem Complex environments require efficient and specialized decision-making.
method Decomposes policy into competitive primitives that decide based on information needs, regularized to use minimal information.
result Improves generalization over flat and hierarchical policies.
Novel evolutionary strategy solves stochastic constrained optimization problems.
problem Optimizing objective functions with stochastic constraints in reinforcement learning.
method Design of a novel optimization algorithm with a sufficient decrease mechanism for stochastic constrained problems.
result Demonstrated convergence of the algorithm on control tasks and constrained optimization problems.
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
This paper optimizes driver repositioning using MARL and reward design for better service and traffic management.
problem Unserved passenger requests due to drivers' cruising behavior during passenger seeking.
method Mean field multi-agent reinforcement learning (MARL) with a reward design scheme and Bayesian optimization (BO) to solve bilevel optimization problems.
result Optimal toll charges and service charges can improve platform and city planner objectives by significant margins, leading to better traffic conditions.
Unsupervised meta-learning speeds up reinforcement learning tasks.
problem Efficiently solving new reinforcement learning tasks.
method Formulating unsupervised meta-reinforcement learning and using mutual information for task proposals.
result Unsupervised meta-reinforcement learning effectively acquires accelerated procedures without manual task design.
Double descent found in DRL, improving generalization with model capacity.
problem Generalization in over-parameterized DRL models.
method Actor-Critic framework, Policy Entropy metric.
result Policy Entropy significantly reduces as model capacity increases, indicating improved generalization.
Paper connects RL and non-equilibrium statistical mechanics for entropy-regularized RL.
problem Obtaining analytical solutions for entropy-regularized RL.
method Mapping RL to non-equilibrium statistical mechanics, applying large deviation theory.
result Derives exact analytical results for optimal policy and dynamics in MDPs.