This work proposes a new framework for a socially-aware dynamic local planner in crowded environments by building on the recently proposed Trajectory-ranked Maximum Entropy Deep Inverse Reinforcement Learning (T-MEDIRL). To address the social navigation problem, our multi-modal learning planner explicitly considers social interaction factors, as well as social-awareness factors into T-MEDIRL pipeline to learn a reward function from human demonstrations. Moreover, we propose a novel trajectory ranking score using the sudden velocity change of pedestrians around the robot to address the sub-optimality in human demonstrations. Our evaluation shows that this method can successfully make a robot navigate in a crowded social environment and outperforms the state-of-art social navigation methods in terms of the success rate, navigation time, and invasion rate.
相關內容
Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In this article, we consider the simplest yet hard to tackle generalization setting where the test environment is unknown at train time, forcing the agent to adapt to the system's new dynamics. This online adaptation process can be computationally expensive (e.g., fine-tuning) and cannot rely on meta-RL techniques since there is just a single train environment. To do so, we propose an approach where we learn a subspace of policies within the parameter space. This subspace contains an infinite number of policies that are trained to solve the training environment while having different parameter values. As a consequence, two policies in that subspace process information differently and exhibit different behaviors when facing variations of the train environment. Our experiments carried out over a large variety of benchmarks compare our approach with baselines, including diversity-based methods. In comparison, our approach is simple to tune, does not need any extra component (e.g., discriminator) and learns policies able to gather a high reward on unseen environments.
Intelligence agents and multi-agent systems play important roles in scenes like the control system of grouped drones, and multi-agent navigation and obstacle avoidance which is the foundational function of advanced application has great importance. In multi-agent navigation and obstacle avoidance tasks, the decision-making interactions and dynamic changes of agents are difficult for traditional route planning algorithms or reinforcement learning algorithms with the increased complexity of the environment. The classical multi-agent reinforcement learning algorithm, Multi-agent deep deterministic policy gradient(MADDPG), solved precedent algorithms' problems of having unstationary training process and unable to deal with environment randomness. However, MADDPG ignored the temporal message hidden beneath agents' interaction with the environment. Besides, due to its CTDE technique which let each agent's critic network to calculate over all agents' action and the whole environment information, it lacks ability to scale to larger amount of agents. To deal with MADDPG's ignorance of the temporal information of the data, this article proposes a new algorithm called MADDPG-LSTMactor, which combines MADDPG with Long short term memory (LSTM). By using agent's observations of continuous timesteps as the input of its policy network, it allows the LSTM layer to process the hidden temporal message. Experimental result demonstrated that this algorithm had better performance in scenarios where the amount of agents is small. Besides, to solve MADDPG's drawback of not being efficient in scenarios where agents are too many, this article puts forward a light-weight MADDPG (MADDPG-L) algorithm, which simplifies the input of critic network. The result of experiments showed that this algorithm had better performance than MADDPG when the amount of agents was large.
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset collected by policies of different expertise levels. It is as simple as supervised learning and Behavior Cloning (BC), but takes advantage of return information. On datasets collected by policies of similar expertise, implicit BC has been shown to match or outperform explicit BC. Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models. We show how implicit models can leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets. Furthermore, we show the close relationship between our implicit methods and other popular RL via Supervised Learning algorithms to provide a unified framework. Finally, we demonstrate the effectiveness of our method on high-dimension manipulation and locomotion tasks.
Motion planning and control are crucial components of robotics applications. Here, spatio-temporal hard constraints like system dynamics and safety boundaries (e.g., obstacles in automated driving) restrict the robot's motions. Direct methods from optimal control solve a constrained optimization problem. However, in many applications finding a proper cost function is inherently difficult because of the weighting of partially conflicting objectives. On the other hand, Imitation Learning (IL) methods such as Behavior Cloning (BC) provide a intuitive framework for learning decision-making from offline demonstrations and constitute a promising avenue for planning and control in complex robot applications. Prior work primarily relied on soft-constraint approaches, which use additional auxiliary loss terms describing the constraints. However, catastrophic safety-critical failures might occur in out-of-distribution (OOD) scenarios. This work integrates the flexibility of IL with hard constraint handling in optimal control. Our approach constitutes a general framework for constraint robotic motion planning and control using offline IL. Hard constraints are integrated into the learning problem in a differentiable manner, via explicit completion and gradient-based correction. Simulated experiments of mobile robot navigation and automated driving provide evidence for the performance of the proposed method.
A good estimation of the actions' cost is key in task planning for human-robot collaboration. The duration of an action depends on agents' capabilities and the correlation between actions performed simultaneously by the human and the robot. This paper proposes an approach to learning actions' costs and coupling between actions executed concurrently by humans and robots. We leverage the information from past executions to learn the average duration of each action and a synergy coefficient representing the effect of an action performed by the human on the duration of the action performed by the robot (and vice versa). We implement the proposed method in a simulated scenario where both agents can access the same area simultaneously. Safety measures require the robot to slow down when the human is close, denoting a bad synergy of tasks operating in the same area. We show that our approach can learn such bad couplings so that a task planner can leverage this information to find better plans.
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show how to integrate value decomposition into a broad class of actor-critic algorithms and use it to assist in the iterative agent-design process. Value decomposition separates a reward function into distinct components and learns value estimates for each. These value estimates provide insight into an agent's learning and decision-making process and enable new training methods to mitigate common problems. As a demonstration, we introduce SAC-D, a variant of soft actor-critic (SAC) adapted for value decomposition. SAC-D maintains similar performance to SAC, while learning a larger set of value predictions. We also introduce decomposition-based tools that exploit this information, including a new reward influence metric, which measures each reward component's effect on agent decision-making. Using these tools, we provide several demonstrations of decomposition's use in identifying and addressing problems in the design of both environments and agents. Value decomposition is broadly applicable and easy to incorporate into existing algorithms and workflows, making it a powerful tool in an RL practitioner's toolbox.
Providing densely shaped reward functions for RL algorithms is often exceedingly challenging, motivating the development of RL algorithms that can learn from easier-to-specify sparse reward functions. This sparsity poses new exploration challenges. One common way to address this problem is using demonstrations to provide initial signal about regions of the state space with high rewards. However, prior RL from demonstrations algorithms introduce significant complexity and many hyperparameters, making them hard to implement and tune. We introduce Monte Carlo Augmented Actor Critic (MCAC), a parameter free modification to standard actor-critic algorithms which initializes the replay buffer with demonstrations and computes a modified $Q$-value by taking the maximum of the standard temporal distance (TD) target and a Monte Carlo estimate of the reward-to-go. This encourages exploration in the neighborhood of high-performing trajectories by encouraging high $Q$-values in corresponding regions of the state space. Experiments across $5$ continuous control domains suggest that MCAC can be used to significantly increase learning efficiency across $6$ commonly used RL and RL-from-demonstrations algorithms. See //sites.google.com/view/mcac-rl for code and supplementary material.
The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence. In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures. HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs. More specifically, the graph pooling operation adaptively selects a subset of nodes to form an induced subgraph for the subsequent layers. To preserve the integrity of graph's topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. By combining HGP-SL operator with graph neural networks, we perform graph level representation learning with focus on graph classification task. Experimental results on six widely used benchmarks demonstrate the effectiveness of our proposed model.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191