No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Transfer Learning with Demonstration Forgetting for Robotic Manipulator
Abstract
Deep learning and especially deep reinforcement learning usually require huge amount of data for training and simulators using is perspective approach to provide this data. Model trained in simulator can be transferred on real robot without wasting a lot of time to collect data. Training in simulator also allows using of different techniques to speed up convergence and increase resulting performance. One of them is to train feature-based model with access to the whole information about the environment and use it as expert for main image-based model. This reduces earning time and the computational costs that are necessary to obtain quality results with image-based model. In this work we improve idea of behaviour cloning feature agent and make it more flexible with using of expert demonstrations forgetting. We conducted experiments on transfer learning for a robotic manipulator that interacts with complex objects and compared them with classic off-policy approaches.
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system such as friction coefficients and an object’s appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity. Our results were obtained using the same distributed RL system that was used to train OpenAI Five. We also include a video of our results: https://youtu.be/jwSbzNHGflM .
In recent years there have been many successes of using deep representations
in reinforcement learning. Still, many of these applications use conventional
architectures, such as convolutional networks, LSTMs, or auto-encoders. In this
paper, we present a new neural network architecture for model-free
reinforcement learning inspired by advantage learning. Our dueling architecture
represents two separate estimators: one for the state value function and one
for the state-dependent action advantage function. The main benefit of this
factoring is to generalize learning across actions without imposing any change
to the underlying reinforcement learning algorithm. Our results show that this
architecture leads to better policy evaluation in the presence of many
similar-valued actions. Moreover, the dueling architecture enables our RL agent
to outperform the state-of-the-art Double DQN method of van Hasselt et al.
(2015) in 46 out of 57 Atari games.
Experience replay lets online reinforcement learning agents remember and
reuse experiences from the past. In prior work, experience transitions were
uniformly sampled from a replay memory. However, this approach simply replays
transitions at the same frequency that they were originally experienced,
regardless of their significance. In this paper we develop a framework for
prioritizing experience, so as to replay important transitions more frequently,
and therefore learn more efficiently. We use prioritized experience replay in
Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved
human-level performance across many Atari games. DQN with prioritized
experience replay achieves a new state-of-the-art, outperforming DQN with
uniform replay on 42 out of 57 games.
The popular Q-learning algorithm is known to overestimate action values under
certain conditions. It was not previously known whether, in practice, such
overestimations are common, whether this harms performance, and whether they
can generally be prevented. In this paper, we answer all these questions
affirmatively. In particular, we first show that the recent DQN algorithm,
which combines Q-learning with a deep neural network, suffers from substantial
overestimations in some games in the Atari 2600 domain. We then show that the
idea behind the Double Q-learning algorithm, which was introduced in a tabular
setting, can be generalized to work with large-scale function approximation. We
propose a specific adaptation to the DQN algorithm and show that the resulting
algorithm not only reduces the observed overestimations, as hypothesized, but
that this also leads to much better performance on several games.
This article introduces a class of incremental learning procedures specialized for prediction-that is, for using past experience with an incompletely known system to predict its future behavior. Whereas conventional prediction-learning methods assign credit by means of the difference between predicted and actual outcomes, the new methods assign credit by means of the difference between temporally successive predictions. Although such temporal-difference methods have been used in Samuel's checker player, Holland's bucket brigade, and the author's Adaptive Heuristic Critic, they have remained poorly understood. Here we prove their convergence and optimality for special cases and relate them to supervised-learning methods. For most real-world prediction problems, temporal-difference methods require less memory and less peak computation than conventional methods and they produce more accurate predictions. We argue that most problems to which supervised learning is currently applied are really prediction problems of the sort to which temporal-difference methods can be applied to advantage.
Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism. DQfD works by combining temporal difference updates with supervised classification of the demonstrator’s actions. We show that DQfD has better initial performance than Prioritized Dueling Double Deep Q-Networks (PDD DQN) as it starts with better scores on the first million steps on 41 of 42 games and on average it takes PDD DQN 83 million steps to catch up to DQfD’s performance. DQfD learns to out-perform the best demonstration given in 14 of 42 games. In addition, DQfD leverages human demonstrations to achieve state-of-the-art results for 11 games. Finally, we show that DQfD performs better than three related algorithms for incorporating demonstration data into DQN.
We present Hierarchical Deep Q-Network (HDQfD) that won first place in the MineRL competition. The HDQfD works on imperfect demonstrations and utilizes the hierarchical structure of expert trajectories. We introduce the procedure of extracting an effective sequence of meta-actions and subgoals from the demonstration data. We present a structured task-dependent replay buffer and an adaptive prioritizing technique that allow the HDQfD agent to gradually erase poor-quality expert data from the buffer. In this paper, we present the details of the HDQfD algorithm and give the experimental results in the Minecraft domain.
In January 2019, DeepMind revealed AlphaStar to the world---the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II---representing a milestone in the progress of AI. AlphaStar draws on many areas of AI research, including deep learning, reinforcement learning, game theory, and evolutionary computation (EC). In this paper we analyze AlphaStar primarily through the lens of EC, presenting a new look at the system and relating it to many concepts in the field. We highlight some of its most interesting aspects---the use of Lamarckian evolution, competitive co-evolution, and quality diversity. In doing so, we hope to provide a bridge between the wider EC community and one of the most significant AI systems developed in recent times.
We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible. The algorithm decouples acting from learning: the actors interact with their own instances of the environment by selecting actions according to a shared neural network, and accumulate the resulting experience in a shared experience replay memory; the learner replays samples of experience and updates the neural network. The architecture relies on prioritized experience replay to focus only on the most significant data generated by the actors. Our architecture substantially improves the state of the art on the Arcade Learning Environment, achieving better final performance in a fraction of the wall-clock training time.
The next generation of AI applications will continuously interact with the environment and learn from these interactions. These applications impose new and demanding systems requirements, both in terms of performance and flexibility. In this paper, we consider these requirements and present Ray---a distributed system to address them. Ray implements a dynamic task graph computation model that supports both the task-parallel and the actor programming models. To meet the performance requirements of AI applications, we propose an architecture that logically centralizes the system's control state using a sharded storage system and a novel bottom-up distributed scheduler. In our experiments, we demonstrate sub-millisecond remote task latencies and linear throughput scaling beyond 1.8 million tasks per second. We empirically validate that Ray speeds up challenging benchmarks and serves as both a natural and performant fit for an emerging class of reinforcement learning applications and algorithms.
Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative is to use off-the-shelf simulators to render synthetic data for which ground-truth annotations are generated automatically. Unfortunately, models trained purely on simulated data often fail to generalize to the real world. We study how randomized simulated environments and domain adaptation methods can be extended to train a grasping system to grasp novel objects from raw monocular RGB images. We extensively evaluate our approaches with a total of more than 25,000 physical test grasps, studying a range of simulation conditions and domain adaptation methods, including a novel extension of pixel-level domain adaptation that we term the GraspGAN. We show that, by using synthetic data and domain adaptation, we are able to reduce the number of real-world samples needed to achieve a given level of performance by up to 50 times, using only randomly generated simulated objects. We also show that by using only unlabeled real-world data and our GraspGAN methodology, we obtain real-world grasping performance without any real-world labels that is similar to that achieved with 939,777 labeled real-world samples.
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.
End-to-end control for robot manipulation and grasping is emerging as an attractive alternative to traditional pipelined approaches. However, end-to-end methods tend to be either slow to train, exhibit little or no generalisability, or lack the ability to accomplish long-horizon or multi-stage tasks. In this paper, we show how two simple techniques can lead to end-to-end (image to velocity) execution of a multi-stage task that is analogous to a simple tidying routine, without having seen a single real image. This involves locating, reaching for, and grasping a cube, then locating a basket to drop the cube in. The first technique is to utilise the full state from a simulator to collect a series of control velocities which accomplish the task. The second technique is to utilise domain randomisation to allow the controller to generalise to the real world. Our results show that we are able to successfully accomplish the task in the real world with the ability to generalise to novel environments, including those with novel lighting conditions and distractor objects, and the ability to deal with moving objects, including the basket itself. We believe our approach to be simple, highly scalable and capable of learning long-horizon tasks that have so far not been shown with the state-of-the-art in end-to-end robot control.
We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the probability that task-space motion of the gripper will result in successful grasps, using only monocular camera images and independently of camera calibration or the current robot pose. This requires the network to observe the spatial relationship between the gripper and objects in the scene, thus learning hand-eye coordination. We then use this network to servo the gripper in real time to achieve successful grasps. To train our network, we collected over 800,000 grasp attempts over the course of two months, using between 6 and 14 robotic manipulators at any given time, with differences in camera placement and hardware. Our experimental evaluation demonstrates that our method achieves effective real-time control, can successfully grasp novel objects, and corrects mistakes by continuous servoing.
The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Task and Spatial Planning by the Cognitive Agent with Human-like Knowledge Representation
- Aitygulov
Dota 2 with Large Scale Deep Reinforcement Learning
- Openai
Agent57: Outperforming the Atari Human Benchmark
- Puigdomènech Badia
PyRep: Bringing V-REP to Deep Robot Learning
- S James
- M Freese
- A J Davison