We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstrated states. We show that this approach allows an agent to learn robust policies using only a small number of expert demonstrations and self-supervised interactions with the environment. We derive this approach from first principles and compare it empirically to a state-of-the-art imitation learning method, showing that it outperforms or matches its performance on two simulated robot manipulation tasks and demonstrate significantly higher sample efficiency by applying the algorithm on a real robot.

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for driving the RL agent to focus on objects for a period of time and to learn good representations of objects for later object recognition task. We evaluate our proposed algorithm in both with and without extrinsic reward settings. Experiments with end-to-end training in simulated environments with applications to few-shot object recognition demonstrated the effectiveness of the proposed algorithm.

In this paper, we develop a multi-agent reinforcement learning (MARL) framework to obtain online power control policies for a large energy harvesting (EH) multiple access channel, when only the causal information about the EH process and wireless channel is available. In the proposed framework, we model the online power control problem as a discrete-time mean-field game (MFG), and leverage the deep reinforcement learning technique to learn the stationary solution of the game in a distributed fashion. We analytically show that the proposed procedure converges to the unique stationary solution of the MFG. Using the proposed framework, the power control policies are learned in a completely distributed fashion. In order to benchmark the performance of the distributed policies, we also develop a deep neural network (DNN) based centralized as well as distributed online power control schemes. Our simulation results show the efficacy of the proposed power control policies. In particular, the DNN based centralized power control policies provide a very good performance for large EH networks for which the design of optimal policies is intractable using the conventional methods such as Markov decision processes. Further, performance of both the distributed policies is close to the throughput achieved by the centralized policies. The work in this paper will appear in part at IEEE ICASSP 2019 [1] and IEEE WiOpt 2019 [2]. This research has been partly supported by the ERC-PoC 727682 CacheMire project. I. INTRODUCTION Internet-of-things (IoT) [3] networks connect a large number of low power sensors whose lifespan is typically limited by the energy that can be stored in their batteries. In this context, the advent of the energy harvesting (EH) technology [4] promises to prolong the lifespan of IoT networks by enabling the nodes to operate by harvesting energy from environmental sources, e.g., the sun, the wind, etc.

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level lateral decision-making and low-level rule-based trajectory modification, a safe and efficient lane change behavior can be achieved. With the setting of our state representation and reward function, the trained agent is able to take appropriate actions in a real-world-like simulator. The generated policy is evaluated on the simulator for 10 times, and the results demonstrate that the proposed rule-based DQN method outperforms the rule-based approach and the DQN method.

Abstract: "In this talk I will cover some of the recent work out of the Socially Intelligent Machines Lab at UT Austin (http://sim.ece.utexas.edu/research.html). The vision of our research is to enable robots to function in dynamic human environments by allowing them to flexibly adapt their skill set via learning interactions with end-users. We explore the ways in which Machine Learning agents can exploit principles of human social learning, and breakdown assumptions about what "data" will be like, when the source of that data is an average human teacher. I will cover our work on interactive reinforcement learning algorithms that model the attention of the teacher; coupling learning from demonstration with simulation to make the best use of valuable interactions with people; and algorithms for re-using previously learned tasks in new contexts with the help of a teacher's hints and corrections. In the latter part of the talk, I will put on my other hat, as co-founder and CEO of Diligent Robotics (http://diligentrobots.com/about) to tell you about how we are translating our research on adapting to human environments into a commercial product. Our first product, Moxi, is a robot assistant that works alongside and supports clinical care teams in hospitals. Moxi was launched into beta trials late last year, and has been deployed in four hospitals across Texas to date."

Deep reinforcement learning has recently made significant progress in solving computer games and robotic control tasks. A known problem, though, is that policies overfit to the training environment and may not avoid rare, catastrophic events such as automotive accidents. A classical technique for improving the robustness of reinforcement learning algorithms is to train on a set of randomized environments, but this approach only guards against common situations. Recently, robust adversarial reinforcement learning (RARL) was developed, which allows efficient applications of random and systematic perturbations by a trained adversary. A limitation of RARL is that only the expected control objective is optimized; there is no explicit modeling or optimization of risk. Thus the agents do not consider the probability of catastrophic events (i.e., those inducing abnormally large negative reward), except through their effect on the expected objective. In this paper we introduce risk-averse robust adversarial reinforcement learning (RARARL), using a risk-averse protagonist and a risk-seeking adversary. We test our approach on a self-driving vehicle controller. We use an ensemble of policy networks to model risk as the variance of value functions. We show through experiments that a risk-averse agent is better equipped to handle a risk-seeking adversary, and experiences substantially fewer crashes compared to agents trained without an adversary.

We explore deep Reinforcement Learning(RL) algorithms for scalping trading and knew that there is no appropriate trading gym and agent examples. Thus we propose gym and agent like Open AI gym in finance. Not only that, we introduce new RL framework based on our hybrid algorithm which leverages between supervised learning and RL algorithm and uses meaningful observations such order book and settlement data from experience watching scalpers trading. That is very crucial information for traders behavior to be decided. To feed these data into our model, we use spatio-temporal convolution layer, called Conv3D for order book data and temporal CNN, called Conv1D for settlement data. Those are preprocessed by episode filter we developed. Agent consists of four sub agents divided to clarify their own goal to make best decision. Also, we adopted value and policy based algorithm to our framework. With these features, we could make agent mimic scalpers as much as possible. In many fields, RL algorithm has already begun to transcend human capabilities in many domains. This approach could be a starting point to beat human in the financial stock market, too and be a good reference for anyone who wants to design RL algorithm in real world domain. Finally, weexperiment our framework and gave you experiment progress.

This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible. In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree or a neural network. In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful. We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.

The operational space of an autonomous vehicle (AV) can be diverse and vary significantly. This may lead to a scenario that was not postulated in the design phase. Due to this, formulating a rule based decision maker for selecting maneuvers may not be ideal. Similarly, it may not be effective to design an a-priori cost function and then solve the optimal control problem in real-time. In order to address these issues and to avoid peculiar behaviors when encountering unforeseen scenario, we propose a reinforcement learning (RL) based method, where the ego car, i.e., an autonomous vehicle, learns to make decisions by directly interacting with simulated traffic. The decision maker for AV is implemented as a deep neural network providing an action choice for a given system state. In a critical application such as driving, an RL agent without explicit notion of safety may not converge or it may need extremely large number of samples before finding a reliable policy. To best address the issue, this paper incorporates reinforcement learning with an additional short horizon safety check (SC). In a critical scenario, the safety check will also provide an alternate safe action to the agent provided if it exists. This leads to two novel contributions. First, it generalizes the states that could lead to undesirable "near-misses" or "collisions ". Second, inclusion of safety check can provide a safe and stable training environment. This significantly enhances learning efficiency without inhibiting meaningful exploration to ensure safe and optimal learned behavior. We demonstrate the performance of the developed algorithm in highway driving scenario where the trained AV encounters varying traffic density in a highway setting.

An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming principle. In the perspective of brain inspiration, reinforcement learning has gained additional interest in solving decision-making tasks as increasing neuroscientific research demonstrates that significant links exist between reinforcement learning and specific neural substrates. Because of the tremendous research that focuses on human brains and reinforcement learning, scientists have investigated how robots can autonomously tackle complex tasks in the form of a self-driving agent control in a human-like way. In this study, we propose an end-to-end architecture using novel deep-Q-network architecture in conjunction with a recurrence to resolve the problem in the field of simulated self-driving. The main contribution of this study is that we trained the driving agent using a brain-inspired trial-and-error technique, which was in line with the real world situation. Besides, there are three innovations in the proposed learning network: raw screen outputs are the only information which the driving agent can rely on, a weighted layer that enhances the differences of the lengthy episode, and a modified replay mechanism that overcomes the problem of sparsity and accelerates learning. The proposed network was trained and tested under a third-partied OpenAI Gym environment. After training for several episodes, the resulting driving agent performed advanced behaviors in the given scene. We hope that in the future, the proposed brain-inspired learning system would inspire practicable self-driving control solutions.