Planning based on long and short term time series forecasts is a common practice across many industries. In this context, temporal aggregation and reconciliation techniques have been useful in improving forecasts, reducing model uncertainty, and providing a coherent forecast across different time horizons. However, an underlying assumption spanning all these techniques is the complete availability of data across all levels of the temporal hierarchy, while this offers mathematical convenience but most of the time low frequency data is partially completed and it is not available while forecasting. On the other hand, high frequency data can significantly change in a scenario like the COVID pandemic and this change can be used to improve forecasts that will otherwise significantly diverge from long term actuals. We propose a dynamic reconciliation method whereby we formulate the problem of informing low frequency forecasts based on high frequency actuals as a Markov Decision Process (MDP) allowing for the fact that we do not have complete information about the dynamics of the process. This allows us to have the best long term estimates based on the most recent data available even if the low frequency cycles have only been partially completed. The MDP has been solved using a Time Differenced Reinforcement learning (TDRL) approach with customizable actions and improves the long terms forecasts dramatically as compared to relying solely on historical low frequency data. The result also underscores the fact that while low frequency forecasts can improve the high frequency forecasts as mentioned in the temporal reconciliation literature (based on the assumption that low frequency forecasts have lower noise to signal ratio) the high frequency forecasts can also be used to inform the low frequency forecasts.

In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy. While the Bellman equation is uniquely solved by the true value function over all state-action pairs, we find that the Bellman error (the difference between both sides of the equation) is a poor proxy for the accuracy of the value function. In particular, we show that (1) due to cancellations from both sides of the Bellman equation, the magnitude of the Bellman error is only weakly related to the distance to the true value function, even when considering all state-action pairs, and (2) in the finite data regime, the Bellman equation can be satisfied exactly by infinitely many suboptimal solutions. This means that the Bellman error can be minimized without improving the accuracy of the value function. We demonstrate these phenomena through a series of propositions, illustrative toy examples, and empirical analysis in standard benchmark domains.

Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning. Recently, there has been renewed interest in bisimulation metrics as a tool to address this issue; these metrics can be used to learn representations that are, in principle, invariant to irrelevant distractions by measuring behavioural similarity between states. An accurate, unbiased, and scalable estimation of these metrics has proved elusive in continuous state and action scenarios. We propose entangled bisimulation, a bisimulation metric that allows the specification of the distance function between states, and can be estimated without bias in continuous state and action spaces. We show how entangled bisimulation can meaningfully improve over previous methods on the Distracting Control Suite (DCS), even when added on top of data augmentation techniques.

Taking advantage of both vehicle-to-everything (V2X) communication and automated driving technology, connected and automated vehicles are quickly becoming one of the transformative solutions to many transportation problems. However, in a mixed traffic environment at signalized intersections, it is still a challenging task to improve overall throughput and energy efficiency considering the complexity and uncertainty in the traffic system. In this study, we proposed a hybrid reinforcement learning (HRL) framework which combines the rule-based strategy and the deep reinforcement learning (deep RL) to support connected eco-driving at signalized intersections in mixed traffic. Vision-perceptive methods are integrated with vehicle-to-infrastructure (V2I) communications to achieve higher mobility and energy efficiency in mixed connected traffic. The HRL framework has three components: a rule-based driving manager that operates the collaboration between the rule-based policies and the RL policy; a multi-stream neural network that extracts the hidden features of vision and V2I information; and a deep RL-based policy network that generate both longitudinal and lateral eco-driving actions. In order to evaluate our approach, we developed a Unity-based simulator and designed a mixed-traffic intersection scenario. Moreover, several baselines were implemented to compare with our new design, and numerical experiments were conducted to test the performance of the HRL model. The experiments show that our HRL method can reduce energy consumption by 12.70% and save 11.75% travel time when compared with a state-of-the-art model-based Eco-Driving approach.

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying to safety-critical applications. Primal-dual as a prevalent constrained optimization framework suffers from instability issues and lacks optimality guarantees. This paper overcomes the issues from a novel probabilistic inference perspective and proposes an Expectation-Maximization style approach to learn safe policy. We show that the safe RL problem can be decomposed to 1) a convex optimization phase with a non-parametric variational distribution and 2) a supervised learning phase. We show the unique advantages of constrained variational policy optimization by proving its optimality and policy improvement stability. A wide range of experiments on continuous robotic tasks show that the proposed method achieves significantly better performance in terms of constraint satisfaction and sample efficiency than primal-dual baselines.

Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel. Most previous work focuses on designing heuristic rules or distance metrics to check whether a state is novel without considering such a discrimination process that can be learned. In this paper, we propose a novel method called generative adversarial exploration (GAEX) to encourage exploration in RL via introducing an intrinsic reward output from a generative adversarial network, where the generator provides fake samples of states that help discriminator identify those less frequently visited states. Thus the agent is encouraged to visit those states which the discriminator is less confident to judge as visited. GAEX is easy to implement and of high training efficiency. In our experiments, we apply GAEX into DQN and the DQN-GAEX algorithm achieves convincing performance on challenging exploration problems, including the game Venture, Montezuma's Revenge and Super Mario Bros, without further fine-tuning on complicate learning algorithms. To our knowledge, this is the first work to employ GAN in RL exploration problems.

The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve a time-dependent orienteering problem with stochastic weights and time windows (TD-OPSWTW). It focused on two types of learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the setup of the competition, the winning methods, and give an overview of the results. The winning methods described in this work have advanced the state-of-the-art in using AI for stochastic routing problems. Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers.

Multi-agent reinforcement learning (MARL) can model many real world applications. However, many MARL approaches rely on epsilon greedy for exploration, which may discourage visiting advantageous states in hard scenarios. In this paper, we propose a new approach QMIX(SEG) for tackling MARL. It makes use of the value function factorization method QMIX to train per-agent policies and a novel Semantic Epsilon Greedy (SEG) exploration strategy. SEG is a simple extension to the conventional epsilon greedy exploration strategy, yet it is experimentally shown to greatly improve the performance of MARL. We first cluster actions into groups of actions with similar effects and then use the groups in a bi-level epsilon greedy exploration hierarchy for action selection. We argue that SEG facilitates semantic exploration by exploring in the space of groups of actions, which have richer semantic meanings than atomic actions. Experiments show that QMIX(SEG) largely outperforms QMIX and leads to strong performance competitive with current state-of-the-art MARL approaches on the StarCraft Multi-Agent Challenge (SMAC) benchmark.

Recently, incorporating natural language instructions into reinforcement learning (RL) to learn semantically meaningful representations and foster generalization has caught many concerns. However, the semantical information in language instructions is usually entangled with task-specific state information, which hampers the learning of semantically invariant and reusable representations. In this paper, we propose a method to learn such representations called element randomization, which extracts task-relevant but environment-agnostic semantics from instructions using a set of environments with randomized elements, e.g., topological structures or textures, yet the same language instruction. We theoretically prove the feasibility of learning semantically invariant representations through randomization. In practice, we accordingly develop a hierarchy of policies, where a high-level policy is designed to modulate the behavior of a goal-conditioned low-level policy by proposing subgoals as semantically invariant representations. Experiments on challenging long-horizon tasks show that (1) our low-level policy reliably generalizes to tasks against environment changes; (2) our hierarchical policy exhibits extensible generalization in unseen new tasks that can be decomposed into several solvable sub-tasks; and (3) by storing and replaying language trajectories as succinct policy representations, the agent can complete tasks in a one-shot fashion, i.e., once one successful trajectory has been attained.

Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after exploring. In the the tabular setting, it is well known that this is a more difficult problem than PAC RL -- where the agent has access to the reward function during exploration -- with optimal sample complexities in the two settings differing by a factor of $|\mathcal{S}|$, the size of the state space. We show that this separation does not exist in the setting of linear MDPs. We first develop a computationally efficient algorithm for reward-free RL in a $d$-dimensional linear MDP with sample complexity scaling as $\mathcal{O}(d^2/\epsilon^2)$. We then show a matching lower bound of $\Omega(d^2/\epsilon^2)$ on PAC RL. To our knowledge, our approach is the first computationally efficient algorithm to achieve optimal $d$ dependence in linear MDPs, even in the single-reward PAC setting. Our algorithm relies on a novel procedure which efficiently traverses a linear MDP, collecting samples in any given "feature direction", and enjoys a sample complexity scaling optimally in the (linear MDP equivalent of the) maximal state visitation probability. We show that this exploration procedure can also be applied to solve the problem of obtaining "well-conditioned" covariates in linear MDPs.