ترغب بنشر مسار تعليمي؟ اضغط هنا

Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning

142   0   0.0 ( 0 )
 نشر من قبل William Agnew
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. textit{Objects} provide a succinct and causal description of the world, and many recent works have proposed unsupervised object representation learning using priors and losses over static object properties like visual consistency. However, object dynamics and interactions are also critical cues for objectness. In this paper we propose a framework for reasoning about object dynamics and behavior to rapidly determine minimal and task-specific object representations. To demonstrate the need to reason over object behavior and dynamics, we introduce a suite of RGBD MuJoCo object collection and avoidance tasks that, while intuitive and visually simple, confound state-of-the-art unsupervised object representation learning algorithms. We also highlight the potential of this framework on several Atari games, using our object representation and standard RL and planning algorithms to learn dramatically faster than existing deep RL algorithms.



قيم البحث

اقرأ أيضاً

Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the pr oblem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches.
168 - Yuning Mao , Yanru Qu , Yiqing Xie 2020
While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS : (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS, which unifies advanced neural SDS methods and statistical measures used in classical MDS. RL-MMR casts MMR guidance on fewer promising candidates, which restrains the search space and thus leads to better representation learning. Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy. Extensive experiments demonstrate that RL-MMR achieves state-of-the-art performance on benchmark MDS datasets. In particular, we show the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency.
Reinforcement Learning (RL) has made remarkable achievements, but it still suffers from inadequate exploration strategies, sparse reward signals, and deceptive reward functions. These problems motivate the need for a more efficient and directed explo ration. For solving this, a Population-guided Novelty Search (PNS) parallel learning method is proposed. In PNS, the population is divided into multiple sub-populations, each of which has one chief agent and several exploring agents. The role of the chief agent is to evaluate the policies learned by exploring agents and to share the optimal policy with all sub-populations. The role of exploring agents is to learn their policies in collaboration with the guidance of the optimal policy and, simultaneously, upload their policies to the chief agent. To balance exploration and exploitation, the Novelty Search (NS) is employed in chief agents to encourage policies with high novelty while maximizing per-episode performance. The introduction of sub-populations and NS mechanisms promote directed exploration and enables better policy search. In the numerical experiment section, the proposed scheme is applied to the twin delayed deep deterministic (TD3) policy gradient algorithm, and the effectiveness of PNS to promote exploration and improve performance in both continuous control domains and discrete control domains is demonstrated. Notably, the proposed method achieves rewards that far exceed the SOTA methods in Delayed MoJoCo environments.
Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as a n independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrators exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have previously learned. In this work, we aim to exploit this shared subtask structure to increase the efficiency of demonstration-guided RL. We first learn a set of reusable skills from large offline datasets of prior experience collected across many tasks. We then propose Skill-based Learning with Demonstrations (SkiLD), an algorithm for demonstration-guided RL that efficiently leverages the provided demonstrations by following the demonstrated skills instead of the primitive actions, resulting in substantial performance improvements over prior demonstration-guided RL approaches. We validate the effectiveness of our approach on long-horizon maze navigation and complex robot manipulation tasks.
In this paper, we present a new class of Markov decision processes (MDPs), called Tsallis MDPs, with Tsallis entropy maximization, which generalizes existing maximum entropy reinforcement learning (RL). A Tsallis MDP provides a unified framework for the original RL problem and RL with various types of entropy, including the well-known standard Shannon-Gibbs (SG) entropy, using an additional real-valued parameter, called an entropic index. By controlling the entropic index, we can generate various types of entropy, including the SG entropy, and a different entropy results in a different class of the optimal policy in Tsallis MDPs. We also provide a full mathematical analysis of Tsallis MDPs, including the optimality condition, performance error bounds, and convergence. Our theoretical result enables us to use any positive entropic index in RL. To handle complex and large-scale problems, we propose a model-free actor-critic RL method using Tsallis entropy maximization. We evaluate the regularization effect of the Tsallis entropy with various values of entropic indices and show that the entropic index controls the exploration tendency of the proposed method. For a different type of RL problems, we find that a different value of the entropic index is desirable. The proposed method is evaluated using the MuJoCo simulator and achieves the state-of-the-art performance.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا