Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Traditional methods directly restrict the total return variance. Recent methods restrict the per-step reward variance as a proxy. We thoroughly examine the limitations of these variance-based methods, such as sensitivity to numerical scale and hindering of policy learning, and propose to use an alternative risk measure, Gini deviation, as a substitute. We study various properties of this new risk measure and derive a policy gradient algorithm to minimize it. Empirical evaluation in domains where risk-aversion can be clearly defined, shows that our algorithm can mitigate the limitations of variance-based risk measures and achieves high return with low risk in terms of variance and Gini deviation when others fail to learn a reasonable policy.
Multimodal learning has seen great success mining data features from multiple modalities with remarkable model performance improvement. Meanwhile, federated learning (FL) addresses the data sharing problem, enabling privacy-preserved collaborative training to provide sufficient precious data. Great potential, therefore, arises with the confluence of them, known as multimodal federated learning. However, limitation lies in the predominant approaches as they often assume that each local dataset records samples from all modalities. In this paper, we aim to bridge this gap by proposing an Unimodal Training - Multimodal Prediction (UTMP) framework under the context of multimodal federated learning. We design HA-Fedformer, a novel transformer-based model that empowers unimodal training with only a unimodal dataset at the client and multimodal testing by aggregating multiple clients' knowledge for better accuracy. The key advantages are twofold. Firstly, to alleviate the impact of data non-IID, we develop an uncertainty-aware aggregation method for the local encoders with layer-wise Markov Chain Monte Carlo sampling. Secondly, to overcome the challenge of unaligned language sequence, we implement a cross-modal decoder aggregation to capture the hidden signal correlation between decoders trained by data from different modalities. Our experiments on popular sentiment analysis benchmarks, CMU-MOSI and CMU-MOSEI, demonstrate that HA-Fedformer significantly outperforms state-of-the-art multimodal models under the UTMP federated learning frameworks, with 15%-20% improvement on most attributes.
When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints followed by expert agents (e.g., humans) are often hard to specify mathematically and unknown to the RL agents. To tackle these issues, Constraint Inverse Reinforcement Learning (CIRL) considers the formalism of Constrained Markov Decision Processes (CMDPs) and estimates constraints from expert demonstrations by learning a constraint function. As an emerging research topic, CIRL does not have common benchmarks, and previous works tested their algorithms with hand-crafted environments (e.g., grid worlds). In this paper, we construct a CIRL benchmark in the context of two major application domains: robot control and autonomous driving. We design relevant constraints for each environment and empirically study the ability of different algorithms to recover those constraints based on expert trajectories that respect those constraints. To handle stochastic dynamics, we propose a variational approach that infers constraint distributions, and we demonstrate its performance by comparing it with other CIRL baselines on our benchmark. The benchmark, including the information for reproducing the performance of CIRL algorithms, is publicly available at https://github.com/Guiliang/CIRL-benchmarks-public
Inverse reinforcement learning (IRL) methods assume that the expert data is generated by an agent optimizing some reward function. However, in many settings, the agent may optimize a reward function subject to some constraints, where the constraints induce behaviors that may be otherwise difficult to express with just a reward function. We consider the setting where the reward function is given, and the constraints are unknown, and propose a method that is able to recover these constraints satisfactorily from the expert data. While previous work has focused on recovering hard constraints, our method can recover cumulative soft constraints that the agent satisfies on average per episode. In IRL fashion, our method solves this problem by adjusting the constraint function iteratively through a constrained optimization procedure, until the agent behavior matches the expert behavior. Despite the simplicity of the formulation, our method is able to obtain good results. We demonstrate our approach on synthetic environments and real world highway driving data.
We propose a score-based DAG structure learning method for time-series data that captures linear, nonlinear, lagged and instantaneous relations among variables while ensuring acyclicity throughout the entire graph. The proposed method extends nonparametric NOTEARS, a recent continuous optimization approach for learning nonparametric instantaneous DAGs. The proposed method is faster than constraint-based methods using nonlinear conditional independence tests. We also promote the use of optimization constraints to incorporate prior knowledge into the structure learning process. A broad set of experiments with simulated data demonstrates that the proposed method discovers better DAG structures than several recent comparison methods. We also evaluate the proposed method on complex real-world data acquired from NHL ice hockey games containing a mixture of continuous and discrete variables. The code is available at https://github.com/xiangyu-sun-789/NTS-NOTEARS/.
This paper addresses the trade-off between Accuracy and Transparency for deep learning applied to sports analytics. Neural nets achieve great predictive accuracy through deep learning, and are popular in sports analytics. But it is hard to interpret a neural net model and harder still to extract actionable insights from the knowledge implicit in it. Therefore, we built a simple and transparent model that mimics the output of the original deep learning model and represents the learned knowledge in an explicit interpretable way. Our mimic model is a linear model tree, which combines a collection of linear models with a regression-tree structure. The tree version of a neural network achieves high fidelity, explains itself, and produces insights for expert stakeholders such as athletes and coaches. We propose and compare several scalable model tree learning heuristics to address the computational challenge from datasets with millions of data points.
Deep Reinforcement Learning (DRL) has achieved impressive success in many applications. A key component of many DRL models is a neural network representing a Q function, to estimate the expected cumulative reward following a state-action pair. The Q function neural network contains a lot of implicit knowledge about the RL problems, but often remains unexamined and uninterpreted. To our knowledge, this work develops the first mimic learning framework for Q functions in DRL. We introduce Linear Model U-trees (LMUTs) to approximate neural network predictions. An LMUT is learned using a novel on-line algorithm that is well-suited for an active play setting, where the mimic learner observes an ongoing interaction between the neural net and the environment. Empirical evaluation shows that an LMUT mimics a Q function substantially better than five baseline methods. The transparent tree structure of an LMUT facilitates understanding the network's learned knowledge by analyzing feature influence, extracting rules, and highlighting the super-pixels in image inputs.
A variety of machine learning models have been proposed to assess the performance of players in professional sports. However, they have only a limited ability to model how player performance depends on the game context. This paper proposes a new approach to capturing game context: we apply Deep Reinforcement Learning (DRL) to learn an action-value Q function from 3M play-by-play events in the National Hockey League (NHL). The neural network representation integrates both continuous context signals and game history, using a possession-based LSTM. The learned Q-function is used to value players' actions under different game contexts. To assess a player's overall performance, we introduce a novel Game Impact Metric (GIM) that aggregates the values of the player's actions. Empirical Evaluation shows GIM is consistent throughout a play season, and correlates highly with standard success measures and future salary.