Neural Information Processing Systems http://nips.cc/

We propose a Bayesian decision making framework for control of Markov Decision Processes (MDPs) with unknown dynamics and large, possibly continuous, state, action, and parameter spaces in data-poor environments. Most of the existing adaptive controllers for MDPs with unknown dynamics are based on the reinforcement learning framework and rely on large data sets acquired by sustained direct interaction with the system or via a simulator. This is not feasible in many applications, due to ethical, economic, and physical constraints. The proposed framework addresses the data poverty issue by decomposing the problem into an offline planning stage that does not rely on sustained direct interaction with the system or simulator and an online execution stage. In the offline process, parallel Gaussian process temporal difference (GPTD) learning techniques are employed for near-optimal Bayesian approximation of the expected discounted reward over a sample drawn from the prior distribution of unknown parameters. In the online stage, the action with the maximum expected return with respect to the posterior distribution of the parameters is selected. This is achieved by an approximation of the posterior distribution using a Markov Chain Monte Carlo (MCMC) algorithm, followed by constructing multiple Gaussian processes over the parameter space for efficient prediction of the means of the expected return at the MCMC sample. The effectiveness of the proposed framework is demonstrated using a simple dynamical system model with continuous state and action spaces, as well as a more complex model for a metastatic melanoma gene regulatory network observed through noisy synthetic gene expression data.

Multi-robot navigation and path planning in continuous state and action spaces with uncertain environments remains an open challenge. Deep Reinforcement Learning (RL) is one of the most popular paradigms for solving this task, but its real-world application has been limited due to sample inefficiency and long training periods. Moreover, the existing works using RL for multi-robot navigation lack formal guarantees while designing the environment. In this paper, we introduce an efficient and highly customizable environment for continuous-control multi-robot navigation, where the robots must visit a set of regions of interest (ROIs) by following the shortest paths. The task is formally modeled as a Markov Decision Process (MDP). We describe the multi-robot navigation task as an optimization problem and relate it to finding an optimal policy for the MDP. We crafted several variations of the environment and measured the performance using both gradient and non-gradient based RL methods: A2C, PPO, TRPO, TQC, CrossQ and ARS. To show real-world applicability, we deployed our environment to a 3-D agricultural field with uncertainties using the CoppeliaSim robot simulator and measured the robustness by running inference on the learned models. We believe our work will guide the researchers on how to develop MDP-based environments that are applicable to real-world systems and solve them using the existing state-of-the-art RL methods with limited resources and within reasonable time periods.

Markov games (MGs) and multi-agent reinforcement learning (MARL) are studied to model decision making in multi-agent systems. Traditionally, the objective in MG and MARL has been risk-neutral, i.e., agents are assumed to optimize a performance metric such as expected return, without taking into account subjective or cognitive preferences of themselves or of other agents. However, ignoring such preferences leads to inaccurate models of decision making in many real-world scenarios in finance, operations research, and behavioral economics. Therefore, when these preferences are present, it is necessary to incorporate a suitable measure of risk into the optimization objective of agents, which opens the door to risk-sensitive MG and MARL. In this paper, we systemically review the literature on risk sensitivity in MG and MARL that has been growing in recent years alongside other areas of reinforcement learning and game theory. We define and mathematically describe different risk measures used in MG and MARL and individually for each measure, discuss articles that incorporate it. Finally, we identify recent trends in theoretical and applied works in the field and discuss possible directions of future research.

Recent research on reinforcement learning has focused on algo(cid:173) rithms based on the principles of Dynamic Programming (DP). One of the most promising areas of application for these algo(cid:173) rithms is the control of dynamical systems, and some impressive results have been achieved. However, there are significant gaps between practice and theory. In particular, there are no con ver(cid:173) gence proofs for problems with continuous state and action spaces, or for systems involving non-linear function approximators (such as multilayer perceptrons). This paper presents research applying DP-based reinforcement learning theory to Linear Quadratic Reg(cid:173) ulation (LQR), an important class of control problems involving continuous state and action spaces and requiring a simple type of non-linear function approximator. We describe an algorithm based on Q-Iearning that is proven to converge to the optimal controller for a large class of LQR problems.

Advances in reinforcement learning have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We propose building a theoretical understanding of continuous state and action spaces by employing a geometric lens. Central to our work is the idea that the transition dynamics induce a low dimensional manifold of reachable states embedded in the high-dimensional nominal state space. We prove that, under certain conditions, the dimensionality of this manifold is at most the dimensionality of the action space plus one. This is the first result of its kind, linking the geometry of the state space to the dimensionality of the action space. We empirically corroborate this upper bound for four MuJoCo environments. We further demonstrate the applicability of our result by learning a policy in this low dimensional representation. To do so we introduce an algorithm that learns a mapping to a low dimensional representation, as a narrow hidden layer of a deep neural network, in tandem with the policy using DDPG. Our experiments show that a policy learnt this way perform on par or better for four MuJoCo control suite tasks.

Reinforcement learning (RL) gained considerable attention by creating decision-making agents that maximize rewards received from fully observable environments. However, many real-world problems are partially or noisily observable by nature, where agents do not receive the true and complete state of the environment. Such problems are formulated as partially observable Markov decision processes (POMDPs). Some studies applied RL to POMDPs by recalling previous decisions and observations or inferring the true state of the environment from received observations. Nevertheless, aggregating observations and decisions over time is impractical for environments with high-dimensional continuous state and action spaces. Moreover, so-called inference-based RL approaches require large number of samples to perform well since agents eschew uncertainty in the inferred state for the decision-making. Active inference is a framework that is naturally formulated in POMDPs and directs agents to select decisions by minimising expected free energy (EFE). This supplies reward-maximising (exploitative) behaviour in RL, with an information-seeking (exploratory) behaviour. Despite this exploratory behaviour of active inference, its usage is limited to discrete state and action spaces due to the computational difficulty of the EFE. We propose a unified principle for joint information-seeking and reward maximization that clarifies a theoretical connection between active inference and RL, unifies active inference and RL, and overcomes their aforementioned limitations. Our findings are supported by strong theoretical analysis. The proposed framework's superior exploration property is also validated by experimental results on partial observable tasks with high-dimensional continuous state and action spaces. Moreover, the results show that our model solves reward-free problems, making task reward design optional.

This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) with unknown transition probabilities over continuous state and action spaces. Linear temporal logic (LTL) is used to specify high-level tasks over infinite horizon, which can be converted into a limit deterministic generalized B\"uchi automaton (LDGBA) with several accepting sets. The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP by incorporating a synchronous tracking-frontier function to record unvisited accepting sets of the automaton, and to facilitate the satisfaction of the accepting conditions. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states and can overcome the issues of sparse rewards. Rigorous analysis shows that any RL method that optimizes the expected discounted return is guaranteed to find an optimal policy whose traces maximize the satisfaction probability. A modular deep deterministic policy gradient (DDPG) is then developed to generate such policies over continuous state and action spaces. The performance of our framework is evaluated via an array of OpenAI gym environments.

In this paper, we propose a model-free reinforcement learning method to synthesize control policies for motion planning problems for continuous states and actions. The robot is modelled as a labeled Markov decision process (MDP) with continuous state and action spaces. Linear temporal logics (LTL) are used to specify high-level tasks. We then train deep neural networks to approximate the value function and policy using an actor-critic reinforcement learning method. The LTL specification is converted into an annotated limit-deterministic B\"uchi automaton (LDBA) for continuously shaping the reward so that dense reward is available during training. A naive way of solving a motion planning problem with LTL specifications using reinforcement learning is to sample a trajectory and, if the trajectory satisfies the entire LTL formula then we assign a high reward for training. However, the sampling complexity needed to find such a trajectory is too high when we have a complex LTL formula for continuous state and action spaces. As a result, it is very unlikely that we get enough reward for training if all sample trajectories start from the initial state in the automata. In this paper, we propose a method that samples not only an initial state from the state space, but also an arbitrary state in the automata at the beginning of each training episode. We test our algorithm in simulation using a car-like robot and find out that our method can learn policies for different working configurations and LTL specifications successfully.

Abstract-- We develop algorithms with low regret for learning episodic Markov decision processes based on kernel approximation techniques. The algorithms are based on both the Upper Confidence Bound (UCB) as well as Posterior or Thompson Sampling (PSRL) philosophies, and work in the general setting of continuous state and action spaces when the true unknown transition dynamics are assumed to have smoothness induced by an appropriate Reproducing Kernel Hilbert Space (RKHS). I. INTRODUCTION The goal of reinforcement learning (RL) is to learn optimal behavior by repeated interaction with an unknown environment, usually modeled as a Markov Decision Process (MDP). Performance is typically measured by the amount of interaction, in terms of episodes or rounds, needed to arriv e at an optimal (or near-optimal) policy; this is also known as the sample complexity of RL [1]. The sample complexity objective encourages efficient exploration across states a nd actions, but, at the same time, is indifferent to the reward earned during the learning phase.