Our effort is toward unifying GAN and DRL algorithms into a unifying AI model (AGI or general-purpose AI or artificial general intelligence which has general-purpose applications to: (A) offline learning (of stored data) like GAN in (un/semi-/fully-)SL setting such as big data analytics (mining) and visualization; (B) online learning (of real or simulated devices) like DRL in RL setting (with/out environment reward) such as (real or simulated) robotics and control; Our core proposal is adding an (generative/predictive) environment model to the actor-critic (model-free) architecture which results in a model-based actor-critic architecture with temporal-differencing (TD) error and an episodic memory. The proposed AI model is similar to (model-free) DDPG and therefore it's called model-based DDPG. To evaluate it, we compare it with (model-free) DDPG by applying them both to a variety (wide range) of independent simulated robotic and control task environments in OpenAI Gym and Unity Agents. Our initial limited experiments show that DRL and GAN in model-based actor-critic results in an incremental goal-driven intellignce required to solve each task with similar performance to (model-free) DDPG. Our future focus is to investigate the proposed AI model potential to: (A) unify DRL field inside AI by producing competitive performance compared to the best of model-based (PlaNet) and model-free (D4PG) approaches; (B) bridge the gap between AI and robotics communities by solving the important problem of reward engineering with learning the reward function by demonstration;

A research team working at Google's Robotics division and the Georgia Institute of Technology has figured out how to let four-legged robots learn to walk without needing any help from humans. As MIT Technology Review reports, the researchers implemented a deep reinforcement learning framework, which combines a multi-tasking learning procedure, an automatic reset controller, and a framework that's safety-constrained. A robot can train using the framework for 80 minutes at a time to gain experience without human interaction. It learns multiple directions of travel at the same time, allowing it to use a restricted training space effectively (and without ever getting stuck at the edges). At first the robot learns forward and backward motion on a flat surface, then on a soft mattress, and finally on a doormat with crevices. It's also then possible to autonomously teach the ability to turn left and right across the three different surface types.

Papers published at the Neural Information Processing Systems Conference.

Papers published at the Neural Information Processing Systems Conference.

Transporting suspended payloads is challenging for autonomous aerial vehicles because the payload can cause significant and unpredictable changes to the robot's dynamics. These changes can lead to suboptimal flight performance or even catastrophic failure. Although adaptive control and learning-based methods can in principle adapt to changes in these hybrid robot-payload systems, rapid mid-flight adaptation to payloads that have a priori unknown physical properties remains an open problem. We propose a meta-learning approach that "learns how to learn" models of altered dynamics within seconds of post-connection flight data. Our experiments demonstrate that our online adaptation approach outperforms non-adaptive methods on a series of challenging suspended payload transportation tasks. Videos and other supplemental material are available on our website https://sites.google.com/view/meta-rl-for-flight

Deep reinforcement learning (RL) algorithms frequently require prohibitive interaction experience to ensure the quality of learned policies. The limitation is partly because the agent cannot learn much from the many low-quality trials in early learning phase, which results in low learning rate. Focusing on addressing this limitation, this paper makes a twofold contribution. First, we develop an algorithm, called Experience Grafting (EG), to enable RL agents to reorganize segments of the few high-quality trajectories from the experience pool to generate many synthetic trajectories while retaining the quality. Second, building on EG, we further develop an AutoEG agent that automatically learns to adjust the grafting-based learning strategy. Results collected from a set of six robotic control environments show that, in comparison to a standard deep RL algorithm (DDPG), AutoEG increases the speed of learning process by at least 30%.

Papers published at the Neural Information Processing Systems Conference.

Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving. However, previous approaches only output decisions and do not provide information about the agent's confidence in the recommended actions. This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous driving. A method for classifying whether or not an action should be considered safe is also introduced. The performance of the ensemble RPF method is evaluated by training an agent on a highway driving scenario. It is shown that the trained agent can estimate the uncertainty of its decisions and indicate an unacceptable level when the agent faces a situation that is far from the training distribution. Furthermore, within the training distribution, the ensemble RPF agent outperforms a standard Deep Q-Network agent. In this study, the estimated uncertainty is used to choose safe actions in unknown situations. However, the uncertainty information could also be used to identify situations that should be added to the training process.

Sensor-based perception on vehicles are becoming prevalent and important to enhance the road safety. Autonomous driving systems use cameras, LiDAR, and radar to detect surrounding objects, while human-driven vehicles use them to assist the driver. However, the environmental perception by individual vehicles has the limitations on coverage and/or detection accuracy. For example, a vehicle cannot detect objects occluded by other moving/static obstacles. In this paper, we present a cooperative perception scheme with deep reinforcement learning to enhance the detection accuracy for the surrounding objects. By using the deep reinforcement learning to select the data to transmit, our scheme mitigates the network load in vehicular communication networks and enhances the communication reliability. To design, test, and verify the cooperative perception scheme, we develop a Cooperative & Intelligent Vehicle Simulation (CIVS) Platform, which integrates three software components: traffic simulator, vehicle simulator, and object classifier. We evaluate that our scheme decreases packet loss and thereby increases the detection accuracy by up to 12%, compared to the baseline protocol.

Identifying algorithms that flexibly and efficiently discover temporally-extended multi-phase plans is an essential step for the advancement of robotics and model-based reinforcement learning. The core problem of long-range planning is finding an efficient way to search through the tree of possible action sequences. Existing non-learned planning solutions from the Task and Motion Planning (TAMP) literature rely on the existence of logical descriptions for the effects and preconditions for actions. This constraint allows TAMP methods to efficiently reduce the tree search problem but limits their ability to generalize to unseen and complex physical environments. In contrast, deep reinforcement learning (DRL) methods use flexible neural-network-based function approximators to discover policies that generalize naturally to unseen circumstances. However, DRL methods struggle to handle the very sparse reward landscapes inherent to long-range multi-step planning situations. Here, we propose the Curious Sample Planner (CSP), which fuses elements of TAMP and DRL by combining a curiosity-guided sampling strategy with imitation learning to accelerate planning. We show that CSP can efficiently discover interesting and complex temporally-extended plans for solving a wide range of physically realistic 3D tasks. In contrast, standard planning and learning methods often fail to solve these tasks at all or do so only with a huge and highly variable number of training samples. We explore the use of a variety of curiosity metrics with CSP and analyze the types of solutions that CSP discovers. Finally, we show that CSP supports task transfer so that the exploration policies learned during experience with one task can help improve efficiency on related tasks.