اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning Sparse Rewarded Tasks from Sub-Optimal Demonstrations
131
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these methods in real-world scenarios. On the other hand, imitation learning (IL) learns effectively in sparse-rewarded tasks by leveraging the existing expert demonstrations. In practice, collecting a sufficient amount of expert demonstrations can be prohibitively expensive, and the quality of demonstrations typically limits the performance of the learning policy. In this work, we propose Self-Adaptive Imitation Learning (SAIL) that can achieve (near) optimal performance given only a limited number of sub-optimal demonstrations for highly challenging sparse reward tasks. SAIL bridges the advantages of IL and RL to reduce the sample complexity substantially, by effectively exploiting sup-optimal demonstrations and efficiently exploring the environment to surpass the demonstrated performance. Extensive empirical results show that not only does SAIL significantly improve the sample-efficiency but also leads to much better final performance across different continuous control tasks, comparing to the state-of-the-art.
قيم البحث
اقرأ أيضاً
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agents trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP cons
traint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e.g., going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely excluding it. Our numerical experiment in a tabular RL setting demonstrates that the SP constraint can significantly reduce the trajectory space of policy. As a result, our constraint enables more sample efficient learning by suppressing redundant exploration and exploitation. Our experiments on MiniGrid, DeepMind Lab, Atari, and Fetch show that the proposed method significantly improves proximal policy optimization (PPO) and outperforms existing novelty-seeking exploration methods including count-based exploration even in continuous control tasks, indicating that it improves the sample efficiency by preventing the agent from taking redundant actions.
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to as unlabele
d experience: data of mixed and unknown quality without reward annotations. This unlabeled data can be generated by a variety of sources such as human teleoperation, scripted policies and other agents on the same robot. Towards data-driven offline robot learning that can use this unlabeled experience, we introduce Offline Reinforced Imitation Learning (ORIL). ORIL first learns a reward function by contrasting observations from demonstrator and unlabeled trajectories, then annotates all data with the learned reward, and finally trains an agent via offline reinforcement learning. Across a diverse set of continuous control and simulated robotic manipulation tasks, we show that ORIL consistently outperforms comparable BC agents by effectively leveraging unlabeled experience.
In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect a
nd sufficient, which yet is unrealistic to meet in practice. To work on imperfect demonstrations, we first define an imperfect expert setting for RLfD in a formal way, and then point out that previous methods suffer from two issues in terms of optimality and convergence, respectively. Upon the theoretical findings we have derived, we tackle these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem. We further demonstrate that such problem is able to be addressed efficiently by performing a local linear search on its dual form. Considerable empirical evaluations on a comprehensive collection of benchmarks indicate our method attains consistent improvement over other RLfD counterparts.
Learning robotic manipulation through reinforcement learning (RL) using only sparse reward signals is still considered a largely unsolved problem. Leveraging human demonstrations can make the learning process more sample efficient, but obtaining high
-quality demonstrations can be costly or unfeasible. In this paper we propose a novel approach that introduces object-level demonstrations, i.e. examples of where the objects should be at any state. These demonstrations are generated automatically through RL hence require no expert knowledge. We observe that, during a manipulation task, an object is moved from an initial to a final position. When seen from the point of view of the object being manipulated, this induces a locomotion task that can be decoupled from the manipulation task and learnt through a physically-realistic simulator. The resulting object-level trajectories, called simulated locomotion demonstrations (SLDs), are then leveraged to define auxiliary rewards that are used to learn the manipulation policy. The proposed approach has been evaluated on 13 tasks of increasing complexity, and has been demonstrated to achieve higher success rate and faster learning rates compared to alternative algorithms. SLDs are especially beneficial for tasks like multi-object stacking and non-rigid object manipulation.
Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that generalize beyond t
he demonstrated behaviors is still an open challenge. We present a novel imitation learning framework to enable robots to 1) learn complex real world manipulation tasks efficiently from a small number of human demonstrations, and 2) synthesize new behaviors not contained in the collected demonstrations. Our key insight is that multi-task domains often present a latent structure, where demonstrated trajectories for different tasks intersect at common regions of the state space. We present Generalization Through Imitation (GTI), a two-stage offline imitation learning algorithm that exploits this intersecting structure to train goal-directed policies that generalize to unseen start and goal state combinations. In the first stage of GTI, we train a stochastic policy that leverages trajectory intersections to have the capacity to compose behaviors from different demonstration trajectories together. In the second stage of GTI, we collect a small set of rollouts from the unconditioned stochastic policy of the first stage, and train a goal-directed agent to generalize to novel start and goal configurations. We validate GTI in both simulated domains and a challenging long-horizon robotic manipulation domain in the real world. Additional results and videos are available at https://sites.google.com/view/gti2020/ .
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
