A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often requires manual or automated searches to find optimal values. Nonetheless, a noticeable limitation is the high cost of algorithm evaluation for complex models, making the tuning process computationally expensive and time-consuming. In this paper, we propose a framework based on integrating complex event processing and temporal models, to alleviate these trade-offs. Through this combination, it is possible to gain insights about a running RL system efficiently and unobtrusively based on data stream monitoring and to create abstract representations that allow reasoning about the historical behaviour of the RL system. The obtained knowledge is exploited to provide feedback to the RL system for optimising its hyperparameters while making effective use of parallel resources. We introduce a novel history-aware epsilon-greedy logic for hyperparameter optimisation that instead of using static hyperparameters that are kept fixed for the whole training, adjusts the hyperparameters at runtime based on the analysis of the agent's performance over time windows in a single agent's lifetime. We tested the proposed approach in a 5G mobile communications case study that uses DQN, a variant of RL, for its decision-making. Our experiments demonstrated the effects of hyperparameter tuning using history on training stability and reward values. The encouraging results show that the proposed history-aware framework significantly improved performance compared to traditional hyperparameter tuning approaches.

In recent years, Multi-task Learning (MTL) has yielded immense success in Recommender System (RS) applications. However, current MTL-based recommendation models tend to disregard the session-wise patterns of user-item interactions because they are predominantly constructed based on item-wise datasets. Moreover, balancing multiple objectives has always been a challenge in this field, which is typically avoided via linear estimations in existing works. To address these issues, in this paper, we propose a Reinforcement Learning (RL) enhanced MTL framework, namely RMTL, to combine the losses of different recommendation tasks using dynamic weights. To be specific, the RMTL structure can address the two aforementioned issues by (i) constructing an MTL environment from session-wise interactions and (ii) training multi-task actor-critic network structure, which is compatible with most existing MTL-based recommendation models, and (iii) optimizing and fine-tuning the MTL loss function using the weights generated by critic networks. Experiments on two real-world public datasets demonstrate the effectiveness of RMTL with a higher AUC against state-of-the-art MTL-based recommendation models. Additionally, we evaluate and validate RMTL's compatibility and transferability across various MTL models.

Reinforcement learning has shown great potential in solving complex tasks when large amounts of data can be generated with little effort. In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles. However, for tasks that, for instance, involve complex soft robots, devising such models is substantially more challenging. Being able to train effectively in increasingly complicated scenarios with reinforcement learning enables to take advantage of complex systems such as soft robots. Here, we leverage the imbalance in complexity of the dynamics to learn more sample-efficiently. We (i) abstract the task into distinct components, (ii) off-load the simple dynamics parts into the simulation, and (iii) multiply these virtual parts to generate more data in hindsight. Our new method, Hindsight States (HiS), uses this data and selects the most useful transitions for training. It can be used with an arbitrary off-policy algorithm. We validate our method on several challenging simulated tasks and demonstrate that it improves learning both alone and when combined with an existing hindsight algorithm, Hindsight Experience Replay (HER). Finally, we evaluate HiS on a physical system and show that it boosts performance on a complex table tennis task with a muscular robot. Videos and code of the experiments can be found on webdav.tuebingen.mpg.de/his/.

When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a "rationality coefficient" capturing how much noise or entropy we expect to see in the human behavior. Prior work typically sets the rationality level to a constant value, regardless of the type, or quality, of human feedback. However, in many settings, giving one type of feedback (e.g. a demonstration) may be much more difficult than a different type of feedback (e.g. answering a comparison query). Thus, we expect to see more or less noise depending on the type of human feedback. In this work, we advocate that grounding the rationality coefficient in real data for each feedback type, rather than assuming a default value, has a significant positive effect on reward learning. We test this in both simulated experiments and in a user study with real human feedback. We find that overestimating human rationality can have dire effects on reward learning accuracy and regret. We also find that fitting the rationality coefficient to human data enables better reward learning, even when the human deviates significantly from the noisy-rational choice model due to systematic biases. Further, we find that the rationality level affects the informativeness of each feedback type: surprisingly, demonstrations are not always the most informative -- when the human acts very suboptimally, comparisons actually become more informative, even when the rationality level is the same for both. Ultimately, our results emphasize the importance and advantage of paying attention to the assumed human-rationality level, especially when agents actively learn from multiple types of human feedback.

The use of unlicensed spectrum for cellular systems to mitigate spectrum scarcity has led to the development of intelligent adaptive approaches to spectrum access that improve upon traditional carrier sensing and listen-before-talk methods. We study decentralized contention-based medium access for base stations (BSs) of a single Radio Access Technology (RAT) operating on unlicensed shared spectrum. We devise a distributed deep reinforcement learning-based algorithm for both contention and adaptive modulation, modelled on a two state Markov decision process, that attempts to maximize a network-wide downlink throughput objective. Empirically, we find the (proportional fairness) reward accumulated by a policy gradient approach to be significantly higher than even a genie-aided adaptive energy detection threshold. Our approaches are further validated by improved sum and peak throughput. The scalability of our approach to large networks is demonstrated via an improved cumulative reward earned on both indoor and outdoor layouts with a large number of BSs.

Playing an important role in Model-Based Reinforcement Learning (MBRL), environment models aim to predict future states based on the past. Existing works usually ignore instantaneous dependence in the state, that is, assuming that the future state variables are conditionally independent given the past states. However, instantaneous dependence is prevalent in many RL environments. For instance, in the stock market, instantaneous dependence can exist between two stocks because the fluctuation of one stock can quickly affect the other and the resolution of price change is lower than that of the effect. In this paper, we prove that with few exceptions, ignoring instantaneous dependence can result in suboptimal policy learning in MBRL. To address the suboptimality problem, we propose a simple plug-and-play method to enable existing MBRL algorithms to take instantaneous dependence into account. Through experiments on two benchmarks, we (1) confirm the existence of instantaneous dependence with visualization; (2) validate our theoretical findings that ignoring instantaneous dependence leads to suboptimal policy; (3) verify that our method effectively enables reinforcement learning with instantaneous dependence and improves policy performance.

The question of how "smart" active agents, like insects, microorganisms, or future colloidal robots need to steer to optimally reach or discover a target, such as an odor source, food, or a cancer cell in a complex environment has recently attracted great interest. Here, we provide an overview of recent developments, regarding such optimal navigation problems, from the micro- to the macroscale, and give a perspective by discussing some of the challenges which are ahead of us. Besides exemplifying an elementary approach to optimal navigation problems, the article focuses on works utilizing machine learning-based methods. Such learning-based approaches can uncover highly efficient navigation strategies even for problems that involve e.g. chaotic, high-dimensional, or unknown environments and are hardly solvable based on conventional analytical or simulation methods.

Climate-induced disasters are and will continue to be on the rise, and thus search-and-rescue (SAR) operations, where the task is to localize and assist one or several people who are missing, become increasingly relevant. In many cases the rough location may be known and a UAV can be deployed to explore a given, confined area to precisely localize the missing people. Due to time and battery constraints it is often critical that localization is performed as efficiently as possible. In this work we approach this type of problem by abstracting it as an aerial view goal localization task in a framework that emulates a SAR-like setup without requiring access to actual UAVs. In this framework, an agent operates on top of an aerial image (proxy for a search area) and is tasked with localizing a goal that is described in terms of visual cues. To further mimic the situation on an actual UAV, the agent is not able to observe the search area in its entirety, not even at low resolution, and thus it has to operate solely based on partial glimpses when navigating towards the goal. To tackle this task, we propose AiRLoc, a reinforcement learning (RL)-based model that decouples exploration (searching for distant goals) and exploitation (localizing nearby goals). Extensive evaluations show that AiRLoc outperforms heuristic search methods as well as alternative learnable approaches, and that it generalizes across datasets, e.g. to disaster-hit areas without seeing a single disaster scenario during training. We also conduct a proof-of-concept study which indicates that the learnable methods outperform humans on average. Code and models have been made publicly available at https://github.com/aleksispi/airloc.

For general-sum, n-player, strategic games with transferable utility, the Harsanyi-Shapley value provides a computable method to both 1) quantify the strategic value of a player; and 2) make cooperation rational through side payments. We give a simple formula to compute the HS value in normal-form games. Next, we provide two methods to generalize the HS values to stochastic (or Markov) games, and show that one of them may be computed using generalized Q-learning algorithms. Finally, an empirical validation is performed on stochastic grid-games with three or more players. Source code is provided to compute HS values for both the normal-form and stochastic game setting.

Reinforcement learning has been applied to various real-world tasks, including robotic manipulation with large state-action spaces and sparse reward signals [1]. In these tasks, standard reinforcement learning tends to perform a lot of useless exploration and easily fall into local optimal solutions. To eliminate this problem, previous works often use expert demonstrations to aid online learning, which adopt some successful trajectories to guide the exploration process [2, 3]. However, standard learning from demonstration algorithms often assume that the target leaning task is exactly same with the task where demonstrations are collected [4, 5, 6]. Under this assumption, experts need to collect the corresponding demonstration for each new task, which can be expensive and inefficient. In this paper, we consider a new learning setting where expert data is collected under a single task, while the agent is required to solve different new tasks. For instance as shown in Figure 1, a robot arm aims to solve peg-in-hole tasks.The demonstration is collected on a certain type of hole while the target tasks have different hole shapes (changes in environmental dynamics) or position shifts (changes in reward function). This can be challenging as agents cannot directly imitate those demonstrations from mismatched tasks due to dynamics and reward function changes. However, compared to learning from scratch, those demonstrations should still be able to provide some useful information to help exploration.