Abstracted Policy Graphs explain reinforcement learning decisions in context.
problem Inability to verify correctness of reinforcement learning systems.
method Markov chains of abstract states to summarize policies.
result Method generates Abstracted Policy Graphs for deterministic policies.
Policy-GNN optimizes GNN aggregation for diverse node iterations.
problem Optimizing GNN performance by varying aggregation iterations for different nodes.
method Policy-GNN uses a meta-policy framework with deep reinforcement learning to adaptively determine the number of aggregations for each node.
result Policy-GNN significantly outperforms state-of-the-art alternatives on real-world datasets.
Paper tackles active learning for GNNs, reducing annotation costs.
problem Efficiently label nodes on graphs to reduce GNN training costs.
method Formulates as a sequential decision process, trains GNN-based policy network with reinforcement learning.
result Trains a transferable active learning policy that generalizes across different domains.
This work improves policy-based training by proposing an evaluation balance objective for GFlowNets.
problem Reliable estimation of policy divergence under directed acyclic graphs remains challenging.
method Proposes an evaluation balance objective over partial episodes to measure policy divergence and improve policy-based training reliability.
result Evaluation balance strengthens policy-based training reliability and broadens its flexibility.
Proposes a model for multi-agent reinforcement learning with hierarchical graph attention network.
problem Limited transferability of trained policies to new multi-agent tasks.
method Uses hierarchical graph attention network for representation learning and multi-agent actor-critic for policy learning.
result Demonstrates superior performance in mixed cooperative and competitive tasks compared to existing methods.
We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and consider both deterministic and Erdős-Rényi random graph models. For such a graph feedback model, we fir…
A decentralized policy achieves logarithmic regret for multi-agent MAB problems with communication constraints.
problem Decentralized policy for multi-agent MAB problems with option availability and communication constraints.
method Upper Confidence Bound (UCB) algorithms with non-stationary stochastic communication protocol.
result Guaranteed logarithmic regret for non-fully connected spatial graphs with communication constraints.
New approach for open ad hoc teamwork using graph-based policy learning.
problem Designing autonomous agents to collaborate with changing teams without prior coordination.
method Graph-based policy learning to adapt to dynamic team compositions.
result Successfully models the effects of other agents, leading to robust adaptation and superior performance.
This study analyzes economic policy uncertainty indices using visibility graphs.
problem Understanding the role of economic policy uncertainty in global economies.
method Visibility graph algorithm applied to economic policy uncertainty indices.
result The economic policy uncertainty indices exhibit persistent behavior and scale-free networks.
Generating novel graph structures that optimize given objectives while obeying some given underlying rules is fundamental for chemistry, biology and social science research. This is especially important in the task of molecular graph generation, whose goal is to discover novel molecules with desired properties such as …
New algorithm improves graph inference tasks.
problem Complex graph reasoning and prediction tasks.
method Policy Message Passing algorithm reformulates graph inference as stochastic sequential processes.
result Consistently outperforms state-of-the-art models.
Graph Denoising Policy Network learns robust representations from noisy graphs.
problem Noise sensitivity in graph representation learning.
method Reinforcement learning to select signal neighborhoods and aggregate features.
result Significantly outperforms state-of-the-art methods on node classification tasks.
Graph neural nets learn better branch-and-bound policies.
problem Combinatorial optimization problems, especially hard ones.
method Graph convolutional neural network model trained via imitation learning.
result Improves over state-of-the-art methods and expert-designed rules.
Graph neural networks optimize radio resource management policies for wireless networks.
problem Optimizing user selection and power control in wireless networks with fairness constraints.
method Formulated as a Lagrangian dual problem, RRM policies are parameterized by a GNN architecture trained on channel conditions.
result The method achieves superior tradeoff between average and 5th percentile rates, demonstrating fairness.
Placeto learns efficient device placements for any neural network graph.
problem Finding efficient device placements for neural network training.
method Reinforcement learning approach with iterative placement improvements and graph embeddings.
result Placeto requires up to 6.1x fewer training steps and generalizes to unseen graphs.
New algorithm reduces bandit regret by graph domination number.
problem Adversarial multi-armed bandit with partial observations and switching costs.
method New algorithm with improved policy regret bounds.
result Regret depends only on the domination number of the feedback graph.
A new benchmark task for evaluating policy learning in complex, high-dimensional action spaces.
problem Lack of a commonly accepted benchmark for evaluating policy learning in hierarchical tasks with high-dimensional action spaces.
method Proposed DinerDash Gym benchmark and Decomposed Policy Graph Modelling (DPGM) algorithm.
result DPGM achieves significant improvement over baselines and effectively injects domain knowledge.
A deep RL approach learns multi-agent coordination through dynamic graph communication.
problem Learning collaborative policies in multi-agent systems.
method Connectivity Driven Communication (CDC) approach using graph-based attention mechanisms.
result CDC learns effective collaborative policies and outperforms other methods in cooperative navigation tasks.
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…
This work addresses causal inference challenges in networked interference and proposes GNN-based estimators for individual treatment effects.
problem Estimating individual treatment effects in randomized experiments with networked interference.
method Uses Graph Neural Networks (GNNs) to capture network dependencies and derive causal effect estimators.
result Provides policy regret bounds and heuristic error bounds for GNN-based causal estimators under network interference and treatment capacity constraints.
Paper analyzes neural network complexity for planning problems.
problem Understanding neural network complexity for planning policies.
method Circuit complexity analysis for relational neural networks.
result Three classes of planning problems identified based on network complexity.
Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies
problem Training stochastic policies to sample from structured discrete probability distributions
method Deriving policy gradient algorithms for GFlowNets and applying Proximal Policy Optimization
result Improved convergence speed and data efficiency compared to standard GFlowNet training objectives
A new machine learning approach for generating high-quality chordal extensions.
problem Defining the definitive relation between chordal extension and optimization algorithm performance.
method On-policy imitation learning scheme mimicking the minimum degree rule to generate high-quality chordal extensions.
result On-policy imitation learning approach effectively learns the minimum degree policy and produces graphs with desirable fill-in characteristics.
This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.
problem Bounding min-entropy leakage for Blowfish privacy mechanisms.
method Organizing analysis over symmetrical partitions corresponding to orbits of graph automorphism groups.
result Demonstrates a construction meeting the bound with asymptotic equality, showing tightness.
Optimizes wireless network resource management with state-augmented policies.
problem Optimizing network-wide utility with user performance constraints.
method State-augmented parameterization of RRM policy, using dual variables.
result Superior trade-off between mean, minimum, and 5th percentile rates.
A new autoregressive model learns the order of graph generation tasks.
problem Generating graphs in a meaningful order when the canonical order is not obvious.
method Introduces a variant of autoregressive models that dynamically decides the autoregressive order based on data.
result Achieves state-of-the-art results on molecular graph generation benchmarks.
Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.
problem Challenges in applying imitation learning to bimanual robotic tasks.
method Integrates physical robot structure into action prediction using a dynamic spatial-temporal graph and differentiable kinematics.
result Effective generation of kinematics-aware actions in both simulation and real-world environments.
A new layer learns abstract relations from graph structure using finite-state automata.
problem Learning abstract relations from graph structure for program analysis.
method Relaxing the problem into learning finite-state automata policies on a graph-based POMDP and training these policies using implicit differentiation.
result GFSA layer finds shortcuts in grid-world graphs and reproduces simple static analyses on Python programs.
Study optimal adjustment sets for causal policies with hidden variables.
problem Estimating dynamic treatment regimes with hidden variables.
method Developed criteria for graphs without hidden variables to compare estimators, extended to dynamic policies and hidden variables.
result Existence and computation of optimal minimal and globally optimal adjustment sets.
New approach to off-policy evaluation connects causal graph to policy effects.
problem Evaluating policies using observational data from different policies.
method Formalizes off-policy evaluation within a causal graph framework.
result Identifies specific causal estimands and highlights necessary experimental data.
Sparse RSP routing improves graph exploration and classification.
problem Optimal randomized routing and distance measures on weighted graphs.
method Tsallis divergence regularization for sparse RSP.
result Sparse random walk converges to least-cost graph as temperature decreases.
Paper tackles efficient exploration of unseen graph-structured environments.
problem Efficient exploration of unseen graph-structured environments.
method Learning to explore framework using reinforcement learning and graph-structured memory.
result Approach outperforms hand-engineered methods in software testing and real-world applications.
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities. First, we design EscapeRoom environments, where the agent must figure out how to n…
A new decentralized policy for multi-agent MAB problems outperforms random communication.
problem Solving multi-agent multi-armed bandit problems efficiently.
method UCB strategy for individual option selection and communication strategy based on neighbor exploration potential.
result The proposed policy significantly outperforms random communication strategies.
New framework for dynamic causal graph modeling and effect estimation.
problem Dynamic changes in causal relationships over time.
method Score-based causal discovery with autoregressive model structure.
result Dynamic causal graph with time-varying causal relations.
A method for a single policy to solve various tasks across diverse agent morphologies.
problem Generalizing a single policy to solve various tasks across diverse agent morphologies.
method Unified representation and behavior distillation using a morphology-task graph and Transformer architecture.
result Improves multi-task performances compared to baselines, suggesting a promising approach.
Efficient molecular optimization using probabilistic hypergraph grammars and reinforcement learning.
problem Optimizing molecular structures for better performance in various benchmarks.
method Inferred a hypergraph replacement grammar from ChEMBL, used conditional priors for policy model, and applied a modified policy gradient algorithm.
result The approach results in a molecular distribution closer to the training set than using equal or unconditional priors.
Agent learns causal relationships from visual data to perform tasks.
problem Performing tasks in novel environments with latent causal structures.
method Learning-based approach to induce causal graphs from visual observations, using attention mechanisms.
result Effective generalization to new tasks with unseen causal structures.
Deep RL learns effective job shop scheduling rules from raw features.
problem Designing effective priority dispatching rules for job shop scheduling is challenging.
method End-to-end deep reinforcement learning using Graph Neural Networks.
result Agent learns high-quality dispatching rules from raw features and generalizes well to unseen instances.
ESAN improves graph neural networks by processing subgraphs.
problem Limitations of MPNNs in graph isomorphism.
method ESAN represents graphs as sets of subgraphs and processes them with equivariant architectures.
result ESAN increases the expressive power of GNNs and more expressive architectures.
Co-training improves sequential decision-making policies from multiple views.
problem Learning policies in settings with multiple state-action representations.
method Inspired by co-training for classification, we present a co-training framework for sequential decision making.
result Our framework improves upon learning from a single view alone.
A novel fully asynchronous scheme for distributed reinforcement learning over networks.
problem Policy evaluation in distributed reinforcement learning over networks.
method Design of a stochastic average gradient (SAG) based distributed algorithm and push-pull augmented graph approach.
result The proposed algorithm converges at a linear rate of \(\mathcal{O}(c^k)\) with \(c\in(0,1)\) and \(k\) increasing by one per node update.
BLISS optimizes GNN training by adaptively sampling nodes.
problem High computational costs in training GNNs on large graphs.
method Uses Bandit Layer Importance Sampling to dynamically select nodes.
result Improves GNN performance with reduced computational cost.
Paper introduces effect-invariance for better policy generalization.
problem Adapting policies to unseen environments efficiently.
method Introduces effect-invariance, a relaxation of full invariance, and develops testing procedures to test e-invariance directly from data.
result Effect-invariance enables zero-shot and few-shot policy generalization without assuming a causal graph.
New method uses variational inference to handle confounding in imitation learning.
problem Confounding due to different sensory inputs between expert and imitating agent.
method Train variational inference model to infer expert's latent information and use for latent-conditional policy training.
result Algorithm converges to correct interventional policy and achieves asymptotically optimal performance.
ALIAS uses RL to learn DAGs without acyclicity constraints.
problem Efficiently learning DAGs from observational data without acyclicity constraints.
method ALIAS employs RL to generate DAGs in a single step with optimal complexity, bypassing acyclicity constraints.
result ALIAS outperforms state-of-the-art methods in causal discovery.
We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure. In our model, a bipartite graph captures the relationship between actions and a common set of unknowns such that choosing an action reveals observations…
Study compares different levels of supervision for training graph embeddings in wireless networks.
problem Improving power control in wireless interference networks.
method Training graph neural networks (GNNs) with different levels of supervision (supervised, unsupervised, self-supervised).
result Different levels of supervision impact system-level throughput, convergence, and generalization.