We study the offline reinforcement learning (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown Markov Decision Process (MDP) using the data coming from a policy $\mu$. In particular, we consider the sample complexity problems of offline RL for finite-horizon MDPs. Prior works study this problem based on different data-coverage assumptions, and their learning guarantees are expressed by the covering coefficients which lack the explicit characterization of system quantities. In this work, we analyze the Adaptive Pessimistic Value Iteration (APVI) algorithm and derive the suboptimality upper bound that nearly matches \[ O\left(\sum_{h=1}^H\sum_{s_h,a_h}d^{\pi^\star}_h(s_h,a_h)\sqrt{\frac{\mathrm{Var}_{P_{s_h,a_h}}{(V^\star_{h+1}+r_h)}}{d^\mu_h(s_h,a_h)}}\sqrt{\frac{1}{n}}\right). \] In complementary, we also prove a per-instance information-theoretical lower bound under the weak assumption that $d^\mu_h(s_h,a_h)>0$ if $d^{\pi^\star}_h(s_h,a_h)>0$. Different from the previous minimax lower bounds, the per-instance lower bound (via local minimaxity) is a much stronger criterion as it applies to individual instances separately. Here $\pi^\star$ is a optimal policy, $\mu$ is the behavior policy and $d_h^\mu$ is the marginal state-action probability. We call the above equation the intrinsic offline reinforcement learning bound since it directly implies all the existing optimal results: minimax rate under uniform data-coverage assumption, horizon-free setting, single policy concentrability, and the tight problem-dependent results. Later, we extend the result to the assumption-free regime (where we make no assumption on $ \mu$) and obtain the assumption-free intrinsic bound. Due to its generic form, we believe the intrinsic bound could help illuminate what makes a specific problem hard and reveal the fundamental challenges in offline RL.

State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hierarchical framework that leverages a relational planner to provide useful state abstractions for learning. We present a brief overview of this framework and the use of a dynamic probabilistic logic model to design these state abstractions. Our experiments show that RePReL not only achieves better performance and efficient learning on the task at hand but also demonstrates better generalization to unseen tasks.

Plants are dynamic systems that are integral to our existence and survival. Plants face environment changes and adapt over time to their surrounding conditions. We argue that plant responses to an environmental stimulus are a good example of a real-world problem that can be approached within a reinforcement learning (RL)framework. With the objective of controlling a plant by moving the light source, we propose GrowSpace, as a new RL benchmark. The back-end of the simulator is implemented using the Space Colonisation Algorithm, a plant growing model based on competition for space. Compared to video game RL environments, this simulator addresses a real-world problem and serves as a test bed to visualize plant growth and movement in a faster way than physical experiments. GrowSpace is composed of a suite of challenges that tackle several problems such as control, multi-stage learning,fairness and multi-objective learning. We provide agent baselines alongside case studies to demonstrate the difficulty of the proposed benchmark.

Robot learning is a very promising topic for the future of automation and machine intelligence. Future robots should be able to autonomously acquire skills, learn to represent their environment, and interact with it. While these topics have been explored in simulation, real-world robot learning research seems to be still limited. This is due to the additional challenges encountered in the real-world, such as noisy sensors and actuators, safe exploration, non-stationary dynamics, autonomous environment resetting as well as the cost of running experiments for long periods of time. Unless we develop scalable solutions to these problems, learning complex tasks involving hand-eye coordination and rich contacts will remain an untouched vision that is only feasible in controlled lab environments. We propose dual-arm settings as platforms for robot learning. Such settings enable safe data collection for acquiring manipulation skills as well as training perception modules in a robot-supervised manner. They also ease the processes of resetting the environment. Furthermore, adversarial learning could potentially boost the generalization capability of robot learning methods by maximizing the exploration based on game-theoretic objectives while ensuring safety based on collaborative task spaces. In this paper, we will discuss the potential benefits of this setup as well as the challenges and research directions that can be pursued.

Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for a revisit. In this paper, we present Broad-persistent Advising (BPA), a broad-persistent advising approach that retains and reuses the processed information. It not only helps trainers to give more general advice relevant to similar states instead of only the current state but also allows the agent to speed up the learning process. We test the proposed approach in two continuous robotic scenarios, namely, a cart pole balancing task and a simulated robot navigation task. The obtained results show that the performance of the agent using BPA improves while keeping the number of interactions required for the trainer in comparison to the DeepIRL approach.

Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improving customers' long-term satisfaction. A key approach to this goal is offline RL, which aims to learn policies from logged data. However, the high-dimensional action space and the non-stationary dynamics in commercial RS intensify distributional shift issues, making it challenging to apply offline RL methods to RS. To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm. It penalizes the unstable Q-values in the regression target by uncertainty-aware weights, without the need to estimate the behavior policy, suitable for RS with a large number of items. We derive the penalty weights from the variances across an ensemble of Q-functions. To alleviate distributional shift issues at test time, we further introduce the critic framework to integrate the proposed method with classic RS models. Extensive experiments conducted on two real-world datasets show that the proposed method could serve as a gain plugin for existing RS models.

SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms. It is built as an extension of PyTorch: algorithms coded with \SALINA{} can be understood in few minutes by PyTorch users and modified easily. Moreover, SaLinA naturally works with multiple CPUs and GPUs at train and test time, thus being a good fit for the large-scale training use cases. In comparison to existing RL libraries, SaLinA has a very low adoption cost and capture a large variety of settings (model-based RL, batch RL, hierarchical RL, multi-agent RL, etc.). But SaLinA does not only target RL practitioners, it aims at providing sequential learning capabilities to any deep learning programmer.

Deep reinforcement learning has shown its effectiveness in various applications and provides a promising direction for solving tasks with high complexity. In most reinforcement learning algorithms, however, two major issues need to be dealt with - the sample inefficiency and the interpretability of a policy. The former happens when the environment is sparsely rewarded and/or has a long-term credit assignment problem, while the latter becomes a problem when the learned policies are deployed at the customer side product. In this paper, we propose a novel hierarchical reinforcement learning algorithm that mitigates the aforementioned issues by decomposing the original task in a hierarchy and by compounding pretrained primitives with intents. We show how the proposed scheme can be employed in practice by solving a pick and place task with a 6 DoF manipulator.

Reinforcement learning is one of the subfields of machine learning. The machine learning model can gain abilities to make decisions and explore in an unsupervised and complex environment by reinforcement learning. Reinforcement learning models use rewards for their actions to reach their goal/mission/task for what they are used to. So, reinforcement learning is different from supervised and unsupervised learning models. Reward rules are determined in the reinforcement learning algorithms.

HANSON: They've had a chequered past, I'll give you that. The Egyptians seemed to be confusing them for some kind of Gods at some point.