Many reinforcement learning algorithms are built on an assumption that an agent interacts with an environment over fixed-duration, discrete time steps. However, physical systems are continuous in time, requiring a choice of time-discretization granularity when digitally controlling them. Furthermore, such systems do not wait for decisions to be made before advancing the environment state, necessitating the study of how the choice of discretization may affect a reinforcement learning algorithm. In this work, we consider the relationship between the definitions of the continuous-time and discrete-time returns. Specifically, we acknowledge an idiosyncrasy with naively applying a discrete-time algorithm to a discretized continuous-time environment, and note how a simple modification can better align the return definitions. This observation is of practical consideration when dealing with environments where time-discretization granularity is a choice, or situations where such granularity is inherently stochastic.

We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used discount factors and increases further as the discount factor approaches one. In addition, we show that if a problem's rewards are shifted by a constant, then standard methods perform much worse, whereas methods with reward centering are unaffected. Estimating the average reward is straightforward in the on-policy setting; we propose a slightly more sophisticated method for the off-policy setting. Reward centering is a very general idea, so we expect almost every reinforcementlearning algorithm to benefit by the addition of reward centering.

Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expert Iteration approach to policy learning used in AlphaZero, we propose Option Iteration, an analogous approach to option discovery. Rather than learning a single strong policy that is trained to match the search results everywhere, Option Iteration learns a set of option policies trained such that for each state encountered, at least one policy in the set matches the search results for some horizon into the future. Intuitively, this may be significantly easier as it allows the algorithm to hedge its bets compared to learning a single globally strong policy, which may have complex dependencies on the details of the current state. Having learned such a set of locally strong policies, we can use them to guide the search algorithm resulting in a virtuous cycle where better options lead to better search results which allows for training of better options. We demonstrate experimentally that planning using options learned with Option Iteration leads to a significant benefit in challenging planning environments compared to an analogous planning algorithm operating in the space of primitive actions and learning a single rollout policy with Expert Iteration.

In this paper, we study asynchronous stochastic approximation algorithms without communication delays. Our main contribution is a stability proof for these algorithms that extends a method of Borkar and Meyn by accommodating more general noise conditions. We also derive convergence results from this stability result and discuss their application in important average-reward reinforcement learning problems.

Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occurs continually. If deep-learning systems are applied in a continual learning setting, then it is well known that they may fail to remember earlier examples. More fundamental, but less well known, is that they may also lose their ability to learn on new examples, a phenomenon called loss of plasticity. We provide direct demonstrations of loss of plasticity using the MNIST and ImageNet datasets repurposed for continual learning as sequences of tasks. In ImageNet, binary classification performance dropped from 89\% accuracy on an early task down to 77\%, about the level of a linear network, on the 2000th task. Loss of plasticity occurred with a wide range of deep network architectures, optimizers, activation functions, batch normalization, dropout, but was substantially eased by $L^2$-regularization, particularly when combined with weight perturbation. Further, we introduce a new algorithm -- continual backpropagation -- which slightly modifies conventional backpropagation to reinitialize a small fraction of less-used units after each example and appears to maintain plasticity indefinitely.

Importance sampling is a central idea underlying off-policy prediction in reinforcement learning. It provides a strategy for re-weighting samples from a distribution to obtain unbiased estimates under another distribution. However, importance sampling weights tend to exhibit extreme variance, often leading to stability issues in practice. In this work, we consider a broader class of importance weights to correct samples in off-policy learning. We propose the use of $\textit{value-aware importance weights}$ which take into account the sample space to provide lower variance, but still unbiased, estimates under a target distribution. We derive how such weights can be computed, and detail key properties of the resulting importance weights. We then extend several reinforcement learning prediction algorithms to the off-policy setting with these weights, and evaluate them empirically.

The transition model is used to imagine possible outcomes of taking the action/option, which are then evaluated by the value functions to change the policies and the value functions themselves. This process is called planning. Planning, like everything else in the architecture, is expected to be continual and temporally uniform. On every step there will be some amount of planning, perhaps a series of small planning steps, but planning would typically not be complete in a single time step and thus would be slow compared to the speed of agent-environment interaction. Planning is an ongoing process that operates asynchronously, in the background, whenever it can be done without interfering with the first three components, all of which must operate on every time step and are said to run in the foreground.

Value iteration (VI) is a foundational dynamic programming method, important for learning and planning in optimal control and reinforcement learning. VI proceeds in batches, where the update to the value of each state must be completed before the next batch of updates can begin. Completing a single batch is prohibitively expensive if the state space is large, rendering VI impractical for many applications. Asynchronous VI helps to address the large state space problem by updating one state at a time, in-place and in an arbitrary order. However, Asynchronous VI still requires a maximization over the entire action space, making it impractical for domains with large action space. To address this issue, we propose doubly-asynchronous value iteration (DAVI), a new algorithm that generalizes the idea of asynchrony from states to states and actions. More concretely, DAVI maximizes over a sampled subset of actions that can be of any user-defined size. This simple approach of using sampling to reduce computation maintains similarly appealing theoretical properties to VI without the need to wait for a full sweep through the entire action space in each update. In this paper, we show DAVI converges to the optimal value function with probability one, converges at a near-geometric rate with probability 1-delta, and returns a near-optimal policy in computation time that nearly matches a previously established bound for VI. We also empirically demonstrate DAVI's effectiveness in several experiments.

To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress in state abstraction, but, although the theory of time abstraction has been extensively developed based on the options framework, in practice options have rarely been used in planning. One reason for this is that the space of possible options is immense and the methods previously proposed for option discovery do not take into account how the option models will be used in planning. Options are typically discovered by posing subsidiary tasks such as reaching a bottleneck state, or maximizing a sensory signal other than the reward. Each subtask is solved to produce an option, and then a model of the option is learned and made available to the planning process. The subtasks proposed in most previous work ignore the reward on the original problem, whereas we propose subtasks that use the original reward plus a bonus based on a feature of the state at the time the option stops. We show that options and option models obtained from such reward-respecting subtasks are much more likely to be useful in planning and can be learned online and off-policy using existing learning algorithms. Reward respecting subtasks strongly constrain the space of options and thereby also provide a partial solution to the problem of option discovery. Finally, we show how the algorithms for learning values, policies, options, and models can be unified using general value functions.

Many off-policy prediction learning algorithms have been proposed in the past decade, but it remains unclear which algorithms learn faster than others. We empirically compare 11 off-policy prediction learning algorithms with linear function approximation on two small tasks: the Rooms task, and the High Variance Rooms task. The tasks are designed such that learning fast in them is challenging. In the Rooms task, the product of importance sampling ratios can be as large as $2^{14}$ and can sometimes be two. To control the high variance caused by the product of the importance sampling ratios, step size should be set small, which in turn slows down learning. The High Variance Rooms task is more extreme in that the product of the ratios can become as large as $2^{14}\times 25$. This paper builds upon the empirical study of off-policy prediction learning algorithms by Ghiassian and Sutton (2021). We consider the same set of algorithms as theirs and employ the same experimental methodology. The algorithms considered are: Off-policy TD($\lambda$), five Gradient-TD algorithms, two Emphatic-TD algorithms, Tree Backup($\lambda$), Vtrace($\lambda$), and ABTD($\zeta$). We found that the algorithms' performance is highly affected by the variance induced by the importance sampling ratios. The data shows that Tree Backup($\lambda$), Vtrace($\lambda$), and ABTD($\zeta$) are not affected by the high variance as much as other algorithms but they restrict the effective bootstrapping parameter in a way that is too limiting for tasks where high variance is not present. We observed that Emphatic TD($\lambda$) tends to have lower asymptotic error than other algorithms, but might learn more slowly in some cases. We suggest algorithms for practitioners based on their problem of interest, and suggest approaches that can be applied to specific algorithms that might result in substantially improved algorithms.