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.
Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper c…
Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the first combination of self attention and reinforcement learning that is capable …
New neural policies learn multi-agent relationships directly, improving coordination in dynamic environments.
problem Training coordination among varying numbers of agents in reinforcement learning.
method Attentional architecture for shared policies that adapt to each agent's context.
result Superior performance on multi-agent vehicle coordination problem, especially with many agents.
Saccader improves hard attention models for vision tasks.
problem Challenges in training hard attention models with class label supervision.
method Proposes Saccader, a novel hard attention model trained with only class labels and policy gradient optimization.
result Achieves 75% top-1 and 91% top-5 accuracy while attending to less than one-third of the image.
New approach to understand recurrent policies as FSMs without minimization.
problem Minimization of FSMs obscures the semantics of policy decisions.
method Start with unminimized FSM, apply interpretable reductions, use attention tool.
result Reveals insights into policy decisions not previously noticed.
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…
We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies. The space is structured towards answering a particular distribution of questions, which are used in a supervised way to train the attentiona…
Partially observable environments present an important open challenge in the domain of sequential control learning with delayed rewards. Despite numerous attempts during the two last decades, the majority of reinforcement learning algorithms and associated approximate models, applied to this context, still assume Marko…
New framework studies policy learning problems under data scarcity.
problem Learning improving policies when data is insufficient.
method Developed a mathematical framework for policy learning problems.
result Reduced policy learning problems to simpler ones in sample complexity.
DAGR improves navigation by refining goal representations conditioned on the current state.
problem Goal-conditioned reinforcement learning lacks state awareness, leading to inefficient policy recovery.
method DAGR refines static goal embeddings into state-conditioned ones using gated cross-attention with a state-goal discrepancy map.
result DAGR improves navigation tasks on OGBench, matching or outperforming base methods.
Paper proposes a method to control robots of different shapes efficiently.
problem Learning optimal control policies for robots of various shapes is challenging.
method Hierarchical architecture with hypernetworks and fixed attention mechanism.
result Method improves learning performance and generalizes to unseen morphologies.
Deep RL learns 2-opt heuristics to improve TSP solutions.
problem Improving TSP solutions beyond initial heuristics.
method Deep reinforcement learning to learn 2-opt operations.
result Learned policies improve solutions faster than previous methods.
A new imitation learning method uses random search for simple policies, outperforming complex models.
problem Complexity and reward dependency issues in imitation learning.
method Derivative-free optimization with simple linear policies and random search.
result The proposed method achieves competitive performance on MuJoCo locomotion tasks without a direct reward signal.
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.
Minimum attention improves reinforcement learning performance in high-dimensional dynamics.
problem Improving reinforcement learning performance in high-dimensional nonlinear dynamics.
method Applying minimum attention as a regularization technique in reinforcement learning, including model-based and model-free approaches.
result Minimum attention outperforms state-of-the-art algorithms in few-shot adaptation and variance reduction.
This paper bridges the gap between theoretical and practical OPE for bandit problems.
problem Estimating the value of a target policy from samples generated by different policies.
method Categorizing OPE situations based on evaluation policy properties, proposing a meta-algorithm.
result Meta-algorithm successfully bridges the gap between theoretical and practical OPE for bandit problems.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.
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.
Improves sample efficiency in reinforcement learning with input representation.
problem Poor sample efficiency in reinforcement learning.
method Attention-based method to project inputs into an invariant representation space.
result Representation space is m! smaller for inputs of m objects, improving sample efficiency. In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observabilit…
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
Improved hyperparameter optimization using simplified Transformer blocks.
problem Discovering optimal architectures in high-dimensional search spaces with limited exploration budgets.
method Simplified Transformer block for modeling hyper-parameter dependencies, actor-critic style algorithm, ensembling.
result Outperformed most algorithms on NAS-Bench-101 and Random Search in discovering more accurate model architectures.
We study a policy gradient method with L2 regularization for MAB problems.
problem Improving policy gradient methods for MAB problems with regularization.
method Investigate convergence of a policy gradient algorithm with L2 regularization for MAB.
result Prove convergence under appropriate technical hypotheses and show practical improvements.
Unified framework for analyzing pessimism in off-policy learning with regularized importance sampling.
problem High variance in importance weighting for off-policy learning.
method Unified PAC-Bayesian study of pessimism with regularized importance sampling.
result Derivation of a tractable PAC-Bayesian generalization bound for common importance weight regularizations.
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.
Wasserstein Policy Learning for Distributional Outcomes
problem Offline policy learning with distribution-valued outcomes
method Establishing statistical guarantees for policy learning framework
result Proven leading dependence on N and N-dim(Π) for finite-sample regret
Develops a framework for identifying mispriced assets through attention factors for statistical arbitrage.
problem Identifying mispriced assets in statistical arbitrage trading.
method Uses conditional latent factors learned from firm characteristic embeddings to identify time-series signals and form a trading strategy.
result Achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period.
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to properly memorize and utilize the long-term history is crucial. In this work, we pro…
We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task. While our goal could in principle be tackled by general reinforcement learning, our particular setting is constrained enough to allow more efficient algorithms. In this paper, we work under t…
This paper improves transportation efficiency by teaching automated vehicles to cooperate.
problem Improving efficiency and safety of transportation systems with automated vehicles.
method Multi-agent graph reinforcement learning with attention mechanism.
result Automated vehicles can achieve better performance when learning to cooperate with each other.
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…
Foreign policy analysis has been struggling to find ways to measure policy preferences and paradigm shifts in international political systems. This paper presents a novel, potential solution to this challenge, through the application of a neural word embedding (Word2vec) model on a dataset featuring speeches by heads o…
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.
Develops a method to estimate optimal policy value in online learning.
problem Challenges in evaluating ongoing policies in online learning environments.
method Doubly Robust Interval Estimation (DREAM) method.
result Valid inference on online conditional mean estimator with asymptotically normal distribution.
A new framework uses deep reinforcement learning to improve aircraft separation in busy airspace.
problem Improving aircraft separation in high-density, dynamic airspace constrained by human controllers.
method Proximal Policy Optimization with an attention network for distributed vehicle autonomy.
result The framework significantly reduces offline training time and increases performance.
Paper tackles offline SSP with value iteration for policy evaluation and learning.
problem Goal-oriented RL with offline data and cost minimization.
method Simple value iteration algorithms for OPE and offline policy learning.
result Strong instance-dependent bounds implying near-minimax optimal worst-case bounds.
The paper presents a model-free method for stabilizing unknown control systems.
problem Stabilizing unknown control systems in engineering.
method Solving discounted LQR problems with increasing discount factors.
result The method efficiently recovers a stabilizing controller for linear and smooth nonlinear systems.
Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.
problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.
New method for natural policy gradients converges linearly.
problem Improving natural policy gradient methods for better convergence.
method Fisher-Rao gradient flow applied to state-action distributions.
result Linear convergence rate with geometry-dependent factor.
Two computational models analyze political topics in social media tweets.
problem Measuring political attention in social media is labor-intensive and restrictive.
method Two computational models: supervised classifier and unsupervised topic model.
result Models provide different benefits: supervised classifier reduces labor, unsupervised model uncovers political and non-political uses.
Regularization improves policy optimization in RL, especially on harder tasks.
problem Lack of conventional regularization in RL methods.
method Comprehensive study of regularization techniques on policy networks with multiple RL algorithms.
result Conventional regularization techniques significantly improve policy optimization, especially on harder tasks.
A decentralized routing framework for lunar exploration robots.
problem Routing data in intermittent connectivity lunar networks.
method Graph Attention-based Multi-Agent Reinforcement Learning (GAT-MARL).
result Higher delivery rates, no duplications, fewer packet losses.
Backpropagation and the chain rule of derivatives have been prominent; however, the total derivative rule has not enjoyed the same amount of attention. In this work we show how the total derivative rule leads to an intuitive visual framework for creating gradient estimators on graphical models. In particular, previous …
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.
MIDAS learns to adaptively control other cars in urban driving scenarios.
problem Autonomous vehicles need to interact with other agents on the road.
method Reinforcement learning with attention mechanism to handle multiple agents.
result MIDAS policies are adaptive and robust to external changes.
SDPA is shown to be an optimal transport problem in deep learning.
problem The mathematical foundation and optimization perspective of SDPA.
method SDPA is shown to be the exact solution to a degenerate, one-sided Entropic Optimal Transport (EOT) problem.
result The SDPA mechanism is a principled mechanism where the forward pass performs optimal inference and the backward pass implements a rational, manifold-aware learning update.
A framework schedules hyperparameters for model-based reinforcement learning, improving performance.
problem Inadequate scheduling of hyperparameters in model-based reinforcement learning.
method Theoretical analysis and AutoMBPO framework to automatically schedule real data ratio and other hyperparameters.
result Training with hyperparameters scheduled by AutoMBPO significantly improves performance.