Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to discover them on their own without any supervision beyond these sparse rewards. While much of the power of reinforcement learning derives from the concept that agents can learn with little guidance, this requirement greatly burdens the training process. If we relax this one restriction and endow the agent with knowledge of the reward function, and in particular of the goal, we can leverage backwards induction to accelerate training. To achieve this, we propose training a model to learn to take imagined reversal steps from known goal states. Rather than training an agent exclusively to determine how to reach a goal while moving forwards in time, our approach travels backwards to jointly predict how we got there. We evaluate our work in Gridworld and Towers of Hanoi and empirically demonstrate that it yields better performance than standard DDQN.

Unfair pricing policies have been shown to be one of the most negative perceptions customers can have concerning pricing, and may result in long-term losses for a company. Despite the fact that dynamic pricing models help companies maximize revenue, fairness and equality should be taken into account in order to avoid unfair price differences between groups of customers. This paper shows how to solve dynamic pricing by using Reinforcement Learning (RL) techniques so that prices are maximized while keeping a balance between revenue and fairness. We demonstrate that RL provides two main features to support fairness in dynamic pricing: on the one hand, RL is able to learn from recent experience, adapting the pricing policy to complex market environments; on the other hand, it provides a trade-off between short and long-term objectives, hence integrating fairness into the model's core. Considering these two features, we propose the application of RL for revenue optimization, with the additional integration of fairness as part of the learning procedure by using Jain's index as a metric. Results in a simulated environment show a significant improvement in fairness while at the same time maintaining optimisation of revenue.

In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utility of pushes for a dense pixel-wise sampling of end effector orientations and locations, while the other does the same for grasping. Both networks are trained jointly in a Q-learning framework and are entirely self-supervised by trial and error, where rewards are provided from successful grasps. In this way, our policy learns pushing motions that enable future grasps, while learning grasps that can leverage past pushes. During picking experiments in both simulation and real-world scenarios, we find that our system quickly learns complex behaviors amid challenging cases of clutter, and achieves better grasping success rates and picking efficiencies than baseline alternatives after only a few hours of training. We further demonstrate that our method is capable of generalizing to novel objects. Qualitative results (videos), code, pre-trained models, and simulation environments are available at http://vpg.cs.princeton.edu

With the advent of sequential matching (of supply and demand) systems (uber, Lyft, Grab for taxis; ubereats, deliveroo, etc for food; amazon prime, lazada etc. for groceries) across many online and offline services, individuals (taxi drivers, delivery boys, delivery van drivers, etc.) earn more by being at the "right" place at the "right" time. We focus on learning techniques for providing guidance (on right locations to be at right times) to individuals in the presence of other "learning" individuals. Interactions between indivduals are anonymous, i.e, the outcome of an interaction (competing for demand) is independent of the identity of the agents and therefore we refer to these as Anonymous MARL settings. Existing research of relevance is on independent learning using Reinforcement Learning (RL) or on Multi-Agent Reinforcement Learning (MARL). The number of individuals in aggregation systems is extremely large and individuals have their own selfish interest (of maximising revenue). Therefore, traditional MARL approaches are either not scalable or assumptions of common objective or action coordination are not viable. In this paper, we focus on improving performance of independent reinforcement learners, specifically the popular Deep Q-Networks (DQN) and Advantage Actor Critic (A2C) approaches by exploiting anonymity. Specifically, we control non-stationarity introduced by other agents using entropy of agent density distribution. We demonstrate a significant improvement in revenue for individuals and for all agents together with our learners on a generic experimental set up for aggregation systems and a real world taxi dataset.

In this case, practitioners would have data with known inputs and known outputs and use a supervised learning algorithm to determine the relationship between them and extract it to apply toward future planning. This is used for data that is unlabeled, meaning there is some uncertainty surrounding what the data represents. Supply chain practitioners would use this algorithm to find hidden relationships in the data to highlight new patterns. This allows practitioners to take in as much data as possible and have the unsupervised learning algorithm organize it in a more meaningful way. A good example would be attempting to solve a 1,000-piece puzzle where every puzzle piece was colored black.

Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson sampling, and random exploration do not help with ARL. We relate ARL in tabular environments to Bayes-Adaptive MDPs. We provide an ARL algorithm using Monte-Carlo Tree Search that is asymptotically Bayes optimal. Experimentally, this algorithm is near-optimal on small Bandit problems and MDPs. On larger MDPs it outperforms a Q-learner augmented with specialised heuristics for ARL. By analysing exploration behaviour in detail, we uncover obstacles to scaling up simulation-based algorithms for ARL.

Artificial Intelligence agents created by Google's DeepMind has taught itself to walk without receiving any human instructions beyond the task to somehow move forward. This reinforcement learning helps an AI to move efficiently in an unknown terrain without programming.

Regardless of whether the learner is a human or machine, the basic learning process is similar. Machine learning algorithms are divided into categories according to their purpose. There are lots of overlaps in which ML algorithms are applied to a particular problem. As a result, for the same problem, there could be many different ML models possible. So, coming out with the best ML model is an art that requires a lot of patience and trial and error.

Artificial intelligence doesn't compare favorably to humans when it comes to problem solving. Ask any eight year old child to place a few blocks on a grid in Minecraft and they'll almost certainly be bored by the task. Stephan Alaniz, a researcher with the Department of Electrical Engineering and Computer Science Technische Universitat Berlin, yesterday published a white paper titled "Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft." In his paper the scientist explains his efforts to create a superior method for training an AI to perform simple tasks based on visual input. If we're ever going to have robots that can live and work among humans seamlessly without damaging us or our property they're going to have to understand how to interact with the environment using visual context. One of the most popular ways to train AI for this task is using video games with simple controls.

Here we propose using the successor representation (SR) to accelerate learning in a constructive knowledge system based on general value functions (GVFs). In real-world settings like robotics for unstructured and dynamic environments, it is infeasible to model all meaningful aspects of a system and its environment by hand due to both complexity and size. Instead, robots must be capable of learning and adapting to changes in their environment and task, incrementally constructing models from their own experience. GVFs, taken from the field of reinforcement learning (RL), are a way of modeling the world as predictive questions. One approach to such models proposes a massive network of interconnected and interdependent GVFs, which are incrementally added over time. It is reasonable to expect that new, incrementally added predictions can be learned more swiftly if the learning process leverages knowledge gained from past experience. The SR provides such a means of separating the dynamics of the world from the prediction targets and thus capturing regularities that can be reused across multiple GVFs. As a primary contribution of this work, we show that using SR-based predictions can improve sample efficiency and learning speed in a continual learning setting where new predictions are incrementally added and learned over time. We analyze our approach in a grid-world and then demonstrate its potential on data from a physical robot arm.