Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep multi-agent RL based on mean embeddings of distributions. We treat the agents as samples of a distribution and use the empirical mean embedding as input for a decentralized policy. We define different feature spaces of the mean embedding using histograms, radial basis functions and a neural network learned end-to-end. We evaluate the representation on two well known problems from the swarm literature (rendezvous and pursuit evasion), in a globally and locally observable setup. For the local setup we furthermore introduce simple communication protocols. Of all approaches, the mean embedding representation using neural network features enables the richest information exchange between neighboring agents facilitating the development of more complex collective strategies.

MDPs extended with LTLf/LDLf non-Markovian rewards have recently attracted interest as a way to specify rewards declaratively. In this paper, we discuss how a reinforcement learning agent can learn policies fulfilling LTLf/LDLf goals. In particular we focus on the case where we have two separate representations of the world: one for the agent, using the (predefined, possibly low-level) features available to it, and one for the goal, expressed in terms of high-level (human-understandable) fluents. We formally define the problem and show how it can be solved. Moreover, we provide experimental evidence that keeping the RL agent feature space separated from the goal's can work in practice, showing interesting cases where the agent can indeed learn a policy that fulfills the LTLf/LDLf goal using only its features (augmented with additional memory).

Machine learning algorithms have found several applications in the field of robotics and control systems. The control systems community has started to show interest towards several machine learning algorithms from the sub-domains such as supervised learning, imitation learning and reinforcement learning to achieve autonomous control and intelligent decision making. Amongst many complex control problems, stable bipedal walking has been the most challenging problem. In this paper, we present an architecture to design and simulate a planar bipedal walking robot(BWR) using a realistic robotics simulator, Gazebo. The robot demonstrates successful walking behaviour by learning through several of its trial and errors, without any prior knowledge of itself or the world dynamics. The autonomous walking of the BWR is achieved using reinforcement learning algorithm called Deep Deterministic Policy Gradient(DDPG). DDPG is one of the algorithms for learning controls in continuous action spaces. After training the model in simulation, it was observed that, with a proper shaped reward function, the robot achieved faster walking or even rendered a running gait with an average speed of 0.83 m/s. The gait pattern of the bipedal walker was compared with the actual human walking pattern. The results show that the bipedal walking pattern had similar characteristics to that of a human walking pattern. The video presenting our experiment is available at https://goo.gl/NHXKqR.

Roderick Bloem TU Graz Austria A prominent problem in artificial intelligence and machine learning is the safe exploration of an environment. In particular, reinforcement learning is a wellknown technique to determine optimal policies for complicated dynamic systems, but suffers from the fact that such policies may induce harmful behavior. We present the concept of a shield that forces decision-making to provably adhere to safety requirements with high probability. Our method exploits the inherent uncertainties in scenarios given by Markov decision processes. We present a method to compute probabilities of decision making regarding temporal logic constraints. We use that information to realize a shield that--when applied to a reinforcement learning algorithm--ensures (near-)optimal behavior both for the safety constraints and for the actual learning objective. In our experiments, we show on the arcade game PAC-MAN that the learning efficiency increases as the learning needs orders of magnitude fewer episodes. We show tradeoffs between sufficient progress in exploration of the environment and ensuring strict safety.

Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and propose a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We demonstrate that this approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.

With an estimated market size of 7.35 billion US dollars, artificial intelligence is growing by leaps and bounds. McKinsey predicts that AI techniques (including deep learning and reinforcement learning) have the potential to create between $3.5T and $5.8T in value annually across nine business functions in 19 industries. Although machine learning is seen as a monolith, this cutting-edge technology is diversified, with various sub-types including machine learning, deep learning, and the state-of-art technology of deep reinforcement learning. Reinforcement learning is the training of machine learning models to make a sequence of decisions. The agent learns to achieve a goal in an uncertain, potentially complex environment.

We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan using hierarchical strategies. We describe the Bayesian Inverse Hierarchical RL (BIHRL) algorithm for inferring the values of hierarchical planners, and use an illustrative toy model to show that BIHRL retains accuracy where standard BIRL fails. Furthermore, BIHRL is able to accurately predict the goals of `Wikispeedia' game players, with inclusion of hierarchical structure in the model resulting in a large boost in accuracy. We show that BIHRL is able to significantly outperform BIRL even when we only have a weak prior on the hierarchical structure of the plans available to the agent, and discuss the significant challenges that remain for scaling up this framework to more realistic settings.

This question might be a little trivial. However, I had a hard time understanding it or finding some formal proof for it. In many papers, it is being said that for estimating the value function, one of the advantages of using temporal difference methods over the Monte Carlo methods in reinforcement learning is that they have a lower variance for computing value function. Up to now, I was not able to find any formal proof for this. Moreover, it is also being said that the Monte Carlo method is less biased when compared with TD methods. If somebody can help me better understand this phenomenon, I would appreciate.

The present work extends the randomized shortest-paths framework (RSP), interpolating between shortest-path and random-walk routing in a network, in three directions. First, it shows how to deal with equality constraints on a subset of transition probabilities and develops a generic algorithm for solving this constrained RSP problem using Lagrangian duality. Second, it derives a surprisingly simple iterative procedure to compute the optimal, randomized, routing policy generalizing the previously developed "soft" Bellman-Ford algorithm. The resulting algorithm allows balancing exploitation and exploration in an optimal way by interpolating between a pure random behavior and the deterministic, optimal, policy (least-cost paths) while satisfying the constraints. Finally, the two algorithms are applied to Markov decision problems by considering the process as a constrained RSP on a bipartite state-action graph. In this context, the derived "soft" value iteration algorithm appears to be closely related to dynamic policy programming as well as Kullback-Leibler and path integral control, and similar to a recently introduced reinforcement learning exploration strategy. This shows that this strategy is optimal in the RSP sense - it minimizes expected path cost subject to relative entropy constraint. Simulation results on illustrative examples show that the model behaves as expected.

Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a model-based reinforcement learning method which combines a learned, factorized transition model of the environment with rollout simulations to learn an effective policy from few examples. The learned transition model employs an abstract, discrete (bottleneck) state, which increases sample efficiency by reducing the number of model parameters and by exploiting structural properties of the environment. We provide a mathematical analysis of the Bottleneck Simulator in terms of fixed points of the learned policy, which reveals how performance is affected by four distinct sources of error: an error related to the abstract space structure, an error related to the transition model estimation variance, an error related to the transition model estimation bias, and an error related to the transition model class bias. Finally, we evaluate the Bottleneck Simulator on two natural language processing tasks: a text adventure game and a real-world, complex dialogue response selection task. On both tasks, the Bottleneck Simulator yields excellent performance beating competing approaches.