Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand. In contrast, model-free reinforcement learning (RL) can acquire behaviors from low-level inputs directly, but often struggles with temporally extended tasks. Can we utilize reinforcement learning to automatically form the abstractions needed for planning, thus obtaining the best of both approaches? We show that goal-conditioned policies learned with RL can be incorporated into planning, so that a planner can focus on which states to reach, rather than how those states are reached. However, with complex state observations such as images, not all inputs represent valid states. We therefore also propose using a latent variable model to compactly represent the set of valid states for the planner, so that the policies provide an abstraction of actions, and the latent variable model provides an abstraction of states. We compare our method with planning-based and model-free methods and find that our method significantly outperforms prior work when evaluated on image-based robot navigation and manipulation tasks that require non-greedy, multi-staged behavior.

MANGA: Method Agnostic Neural-policy Generalization and Adaptation Homanga Bharadhwaj 1, Shoichiro Y amaguchi 2, and Shin-ichi Maeda 2 Abstract -- In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dynamics conditioned policies and efficiently learns to estimate the dynamics parameters of the environment given off-policy state-transition rollouts in the environment. Our scheme is agnostic to the type of training method used - both reinforcement learning (RL) and imitation learning (IL) strategies can be used. We demonstrate the effectiveness of our approach by experimenting with four different MuJoCo agents and comparing against previously proposed transfer baselines. I NTRODUCTION One of the most well recognized goals of robotics research is to develop autonomous agents that can perform a wide variety of tasks in various complex environments. Recently numerous deep reinforcement learning (RL) and imitation learning (IL) based approaches have sought to achieve good performance in complex robotic tasks through minimal supervision. However, a major concern in experimenting with the real environment directly is safety, both of the robot and of the environment. Safety concerns and also the issue of reproducibility has drawn robotics research extensively to simulation environments.

Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments. To enable transfer of policies trained in simulation, randomising simulation parameters leads to more robust policies, but also significantly extends training time. In this paper, we exploit access to privileged information (such as environment states) often available in simulation, in order to improve and accelerate learning over randomised environments. We introduce Attention Privileged Reinforcement Learning (APRiL), which equips the agent with an attention mechanism and makes use of state information in simulation, learning to align attention between state- and image-based policies while additionally sharing generated data. During deployment we can apply the image-based policy to remove the requirement of access to additional information. We experimentally demonstrate accelerated and more robust learning on a number of diverse domains, leading to improved final performance for environments both within and outside the training distribution.

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to assist terrestrial infrastructure for keeping wireless connectivity in various emergency scenarios. To maximize the coverage rate of N ground users (GUs) by jointly placing multiple ABSs with limited coverage range is known to be a NP-hard problem with exponential complexity in N. The problem is further complicated when the coverage range becomes irregular due to site-specific blockage (e.g., buildings) on the air-ground channel in the 3-dimensional (3D) space. To tackle this challenging problem, this paper applies the Deep Reinforcement Learning (DRL) method by 1) representing the state by a coverage bitmap to capture the spatial correlation of GUs/ABSs, whose dimension and associated neural network complexity is invariant with arbitrarily large N; and 2) designing the action and reward for the DRL agent to effectively learn from the dynamic interactions with the complicated propagation environment represented by a 3D Terrain Map. Specifically, a novel two-level design approach is proposed, consisting of a preliminary design based on the dominant line-of-sight (LoS) channel model, and an advanced design to further refine the ABS positions based on site-specific LoS/non-LoS channel states. The double deep Q-network (DQN) with Prioritized Experience Replay (Prioritized Replay DDQN) algorithm is applied to train the policy of multi-ABS placement decision. Numerical results show that the proposed approach significantly improves the coverage rate in complex environment, compared to the benchmark DQN and K-means algorithms.

-- Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations. This architecture is useful for learning tasks in which either the agent does not have access to meaningful states (like position/velocity of robotic joints) or where the observed states significantly deviate from the physical state of the agent (which is commonly the case in low-cost robots in the form of backlash or noisy joint readings). In this work, we introduce Robo-PlaNet, an asynchronous version of PlaNet. This algorithm consistently reaches higher performance in the same amount of time, which we demonstrate in both a simulated and a real robotic experiment. Teaching a robot a new trick can prove challenging. Currently, many methods rely on transfer from simulation to physical platforms (i.e.

Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL). In this paper, we show that intrinsic motivation learning increases the efficiency of exploration, leading to successful subgoal discovery. We introduce a model-free subgoal discovery method based on unsupervised learning over a limited memory of agent's experiences during intrinsic motivation. Additionally, we offer a unified approach to learning representations in model-free HRL.

Representation learning is critical to the success of modern large-scale reinforcement learning systems. Previous works show that sparse representation can effectively reduce catastrophic interference and hence provide relatively stable and consistent boostrap targets when training reinforcement learning algorithms. Tile coding is a well-known sparse feature generation method in reinforcement learning. However, its application is largely restricted to small, low dimensional domains, as its computational and memory requirement grows exponentially as dimension increases. This paper proposes a simple and novel tile coding operation---deep tile coder, which adapts tile coding into deep learning setting, and can be easily scaled to high dimensional problems. The key distinction of our method with previous sparse representation learning method is that, we generate sparse feature by construction, while most previous works focus on designing regularization techniques. We are able to theoretically guarantee sparsity and importantly, our method ensures sparsity from the beginning of learning, without the need of tuning regularization weight. Furthermore, our approach maps from low dimension feature space to high dimension sparse feature space without introducing any additional training parameters. Our empirical demonstration covers classic discrete action control and Mujoco continuous robotics control problems. We show that reinforcement learning algorithms equipped with our deep tile coder achieves superior performance. To our best knowledge, our work is the first to demonstrate successful application of sparse representation learning method in online deep reinforcement learning algorithms for challenging tasks without using a target network.

Adversarial Inverse Reinforcement Learning for Decision Making in Autonomous Driving Pin Wang 1, Dapeng Liu 2, 3, Jiayu Chen 4, and Ching-Y ao Chan 1 Abstract -- Generative Adversarial Imitation Learning (GAIL) is an efficient way to learn sequential control strategies from demonstration. Adversarial Inverse Reinforcement Learning (AIRL) is similar to GAIL but also learns a reward function at the same time and has better training stability. In previous work, however, AIRL has mostly been demonstrated on robotic control in artificial environments. In this paper, we apply AIRL to a practical and challenging problem - the decision-making in autonomous driving, and also augment AIRL with a semantic reward to improve its performance. We use four metrics to evaluate its learning performance in a simulated driving environment. Results show that the vehicle agent can learn decent decision-making behaviors from scratch, and can reach a level of performance comparable with that of an expert. Additionally, the comparison with GAIL shows that AIRL converges faster, achieves better and more stable performance than GAIL. I. INTRODUCTION The application of Reinforcement Learning (RL) in robotics has been very fruitful in recent years.

Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently. How-ever, an issue remains open: in the centralized training process,when the environment for the team is partially observable ornon-stationary, i.e., the observation and action informationof all the agents cannot represent the global states, existingmethods perform poorly and sample inefficiently. Regret Min-imization (RM) can be a promising approach as it performswell in partially observable and fully competitive settings.However, it tends to model others as opponents and thus can-not work well under the CTDE scheme. In this work, wepropose a novel team RM based Bayesian MARL with threekey contributions: (a) we design a novel RM method to traincooperative agents as a team and obtain a team regret-basedpolicy for that team; (b) we introduce a novel method to de-compose the team regret to generate the policy for each agentfor decentralized execution; (c) to further improve the perfor-mance, we leverage a differential particle filter (a SequentialMonte Carlo method) network to get an accurate estimation ofthe state for each agent. Experimental results on two-step ma-trix games (cooperative game) and battle games (large-scalemixed cooperative-competitive games) demonstrate that ouralgorithm significantly outperforms state-of-the-art methods.

Two branches of AI - Deep Learning, and Reinforcement Learning are now responsible for many real-world applications. Machine Translation, Speech Recognition, Object Detection, Robot Control, and Drug Discovery - are some of the numerous examples. Both approaches are data hungry - DL requires many examples of each class, and RL needs to play through many episodes to learn a policy. A small child can typically see an image just once, and instantly recognize it in other contexts and environments. We seem to possess an innate model/representation of how the world works, which helps us grasp new concepts and adapt to new situations fast. Humans are excellent one/few shot learners.