Canada

Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effective way to accelerate learning, but an under-explored dimension for generating a curriculum is the difficulty-to-learn of the subgames –games induced by starting from a specific state. In this work, we present a novel subgame curriculum learning framework for zero-sum games. It adopts an adaptive initial state distribution by resetting agents to some previously visited states where they can quickly learn to improve performance. Building upon this framework, we derive a subgame selection metric that approximates the squared distance to NE values and further adopt a particle-based state sampler for subgame generation. Integrating these techniques leads to our new algorithm, Subgame Automatic Curriculum Learning (SACL), which is a realization of the subgame curriculum learning framework. SACL can be combined with any MARL algorithm such as MAPPO. Experiments in the particle-world environment and Google Research Football environment show SACL produces much stronger policies than baselines. In the challenging hide-and-seek quadrant environment, SACL produces all four emergent stages and uses only half the samples of MAPPO with self-play. The project website is at https://sites.google.com/view/sacl-neurips.

AAAI 2024

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

zero-sum games

multiagent learning

multiagent systems

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

The large action space is one fundamental obstacle to deploying Reinforcement Learning methods in the real world. The numerous redundant actions will cause the agents to make repeated or invalid attempts, even leading to task failure. Although current algorithms conduct some initial explorations for this issue, they either suffer from rule-based systems or depend on expert demonstrations, which significantly limits their applicability in many real-world settings. In this work, we examine the theoretical analysis of what action can be eliminated in policy optimization and propose a novel redundant action filtering mechanism. Unlike other works, our method constructs the similarity factor by estimating the distance between the state distributions, which requires no prior knowledge. In addition, we combine the modified inverse model to avoid extensive computation in high-dimensional state space. We reveal the underlying structure of action spaces and propose a simple yet efficient redundant action filtering mechanism named No Prior Mask (NPM) based on the above techniques. We show the superior performance of our method by conducting extensive experiments on high-dimensional, pixel-input, and stochastic problems with various action redundancy tasks. Our code is public online at https://github.com/zhongdy15/npm.

No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning

We study the distributed gradient aggregation problem where individual clients contribute to learning a central model by sharing parameter gradients constructed from local losses. However, errors in some gradients, caused by low-quality data or adversaries, can degrade the learning process when naively combined. Existing robust gradient aggregation approaches assume that local data represent the global data-generating distribution, which may not always apply to heterogeneous (non-i.i.d.) client data. We propose a new algorithm that can robustly aggregate gradients from potentially heterogeneous clients. Our approach leverages the manifold structure inherent in heterogeneous client gradients and evaluates gradient anomaly degrees by projecting them onto this manifold. This algorithm is implemented as a simple and efficient method that accumulates random projections within the subspace defined by the nearest neighbors within a gradient cloud. Our experiments demonstrate consistent performance improvements over state-of-the-art robust aggregation algorithms.

Robust Distributed Gradient Aggregation Using Projections onto Gradient Manifolds | VIDEO

Reinforcement learning (RL) is broadly employed in human-involved systems to enhance human outcomes. Off-policy evaluation (OPE) has been pivotal for RL in those realms since online policy learning and evaluation can be high-stake. Intelligent tutoring has raised tremendous attentions as highly challenging when applying OPE to human-involved systems, due to that students' subgroups can favor different pedagogical policies and the costly procedure that policies have to be induced fully offline and then directly deployed to the upcoming semester. In this work, we formulate on-demand pedagogical policy selection (ODPS) to tackle the challenges for OPE in intelligent tutoring. We propose a pipeline, EduPlanner, as a concrete solution for ODPS. Our pipeline results in an theoretically unbiased estimator, and enables efficient and customized policy selection by identifying subgroups over both historical data and on-arrival initial logs. We evaluate our approach on the Probability ITS that has been used in real classrooms for over eight years. Our study shows significant improvement on learning outcomes of students with EduPlanner, especially for the ones associated with low-performing subgroups.

Get a Head Start: On-Demand Pedagogical Policy Selection in Intelligent Tutoring

Inferring a diffusion equation from discretely observed measurements is a statistical challenge of significant importance in a variety of fields, from single-molecule tracking in biophysical systems to modeling financial instruments.
Assuming that the underlying dynamical process obeys a d-dimensional stochastic differential equation of the form dx_t = b(x_t)dt + \Sigma(x_t)dw_t, we propose neural network-based estimators of both the drift b and the spatially-inhomogeneous diffusion tensor D = \Sigma\Sigma^T/2 and provide statistical convergence guarantees when b and D are s-Hölder continuous. 
Notably, our bound aligns with the minimax optimal rate N^{-\frac{2s}{2s+d}} for nonparametric function estimation even in the presence of correlation within observational data, which necessitates careful handling when establishing fast-rate generalization bounds.
Our theoretical results are bolstered by numerical experiments demonstrating accurate inference of spatially-inhomogeneous diffusion tensors.

Statistical Spatially Inhomogeneous Diffusion Inference

Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or its representation internal to the network. While margins have been shown to be correlated with the generalization ability of a model when measured at its hidden representations (hidden margins), no such link between large margins and generalization has been established for input margins. We show that while input margins are not generally predictive of generalization, they can be if the search space is appropriately constrained.
We develop such a measure based on input margins, which we refer to as 'constrained margins'. The predictive power of this new measure is demonstrated on the 'Predicting Generalization in Deep Learning' (PGDL) dataset and contrasted with hidden representation margins. We find that constrained margins achieve highly competitive scores and outperform other margin measurements in general. This provides a novel insight on the relationship between generalization and classification margins, and highlights the importance of considering the data manifold for investigations of generalization in DNNs.

Input Margins Can Predict Generalization Too

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware. Inspired by the spiking neuron model, the Delta RNN exploits temporal sparsity during inference by skipping over the update of hidden states from those inactivated neurons whose change of activation across two timesteps is below a defined threshold. This work describes a training algorithm for Delta RNNs that exploits temporal sparsity in the backward propagation phase to reduce computational requirements for training on the edge. Due to the symmetric computation graphs of forward and backward propagation during training, the gradient computation of inactivated neurons can be skipped. Results show a reduction of ∼80% in matrix operations for training a 56k parameter Delta LSTM on the Fluent Speech Commands dataset with negligible accuracy loss. Logic simulations of a hardware accelerator designed for the training algorithm show 2-10X speedup in matrix computations for an activation sparsity range of 50%-90%. Additionally, we show that the proposed Delta RNN training will be useful for online incremental learning on edge devices with limited computing resources.

Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training | VIDEO

This paper studies robust nonparametric regression, in which an adversarial attacker can modify the values of up to q samples from a training dataset of size N. Our initial solution is an M-estimator based on Huber loss minimization. Compared with simple kernel regression, i.e. the Nadaraya-Watson estimator, this method can significantly weaken the impact of malicious samples on the regression performance. We provide the convergence rate as well as the corresponding minimax lower bound. The result shows that, with proper bandwidth selection, supremum error is minimax optimal. The L2 error is optimal with relatively small q, but is suboptimal with larger q. The reason is that this estimator is vulnerable if there are many attacked samples concentrating in a small region. To address this issue, we propose a correction method by projecting the initial estimate to the space of Lipschitz functions. The final estimate is nearly minimax optimal for arbitrary q, up to a logarithmic factor.

Robust Nonparametric Regression under Poisoning Attack

We present a real-time method for robust estimation of multiple instances of geometric models from noisy data.
Geometric models such as vanishing points, planar homographies or fundamental matrices are essential for 3D scene analysis.
Previous approaches discover distinct model instances in an iterative manner, thus limiting their potential for speedup via parallel computation.
In contrast, our method detects all model instances independently and in parallel.
A neural network segments the input data into clusters representing potential model instances by predicting multiple sets of sample and inlier weights.
Using the predicted weights, we determine the model parameters for each potential instance separately in a RANSAC-like fashion.
We train the neural network via task-specific loss functions, i.e. we do not require a ground-truth segmentation of the input data.
As suitable training data for homography and fundamental matrix fitting is scarce, we additionally present two new synthetic datasets.
We demonstrate state-of-the-art performance on these as well as multiple established datasets, with inference times as small as five milliseconds per image.

PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus

In centralized multi-agent systems, often modeled as multi-agent partially observable Markov decision processes (MPOMDPs), the action and observation spaces grow exponentially with the number of agents, making the value and belief state estimation of single-agent online planning ineffective. Prior work partially tackles value estimation by exploiting the inherent structure of multi-agent settings via so-called coordination graphs. Additionally, belief state estimation has been improved by incorporating the likelihood of observations into the approximation. However, the challenges of value estimation and state estimation have only been tackled individually, which prevents these methods from scaling to many agents. Therefore, we address these challenges simultaneously. First, we introduce weighted particle filtering to sample-based online planners in MPOMDPs. Second, we present a scalable approximation of the belief state. Third, we bring an approach that exploits the typical locality of agent interactions to novel online planning algorithms for MPOMDPs operating on a so-called sparse particle filter belief tree. Our experimental evaluation against several state-of-the-art baselines shows that our methods (1) are competitive in settings with only a few agents and (2) improve over the baselines in the presence of many agents.

Factored Online Planning in Many-Agent POMDPs

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.

Downloads

Next from AAAI 2024

No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning

Similar lecture

Safe Subgame Resolving for Extensive Form Correlated Equilibrium