اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNovelty Search makes Evolvability Inevitable
82
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Evolvability is an important feature that impacts the ability of evolutionary processes to find interesting novel solutions and to deal with changing conditions of the problem to solve. The estimation of evolvability is not straightforward and is generally too expensive to be directly used as selective pressure in the evolutionary process. Indirectly promoting evolvability as a side effect of other easier and faster to compute selection pressures would thus be advantageous. In an unbounded behavior space, it has already been shown that evolvable individuals naturally appear and tend to be selected as they are more likely to invade empty behavior niches. Evolvability is thus a natural byproduct of the search in this context. However, practical agents and environments often impose limits on the reach-able behavior space. How do these boundaries impact evolvability? In this context, can evolvability still be promoted without explicitly rewarding it? We show that Novelty Search implicitly creates a pressure for high evolvability even in bounded behavior spaces, and explore the reasons for such a behavior. More precisely we show that, throughout the search, the dynamic evaluation of novelty rewards individuals which are very mobile in the behavior space, which in turn promotes evolvability.
قيم البحث
اقرأ أيضاً
Reward-based optimization algorithms require both exploration, to find rewards, and exploitation, to maximize performance. The need for efficient exploration is even more significant in sparse reward settings, in which performance feedback is given s
paringly, thus rendering it unsuitable for guiding the search process. In this work, we introduce the SparsE Reward Exploration via Novelty and Emitters (SERENE) algorithm, capable of efficiently exploring a search space, as well as optimizing rewards found in potentially disparate areas. Contrary to existing emitters-based approaches, SERENE separates the search space exploration and reward exploitation into two alternating processes. The first process performs exploration through Novelty Search, a divergent search algorithm. The second one exploits discovered reward areas through emitters, i.e. local instances of population-based optimization algorithms. A meta-scheduler allocates a global computational budget by alternating between the two processes, ensuring the discovery and efficient exploitation of disjoint reward areas. SERENE returns both a collection of diverse solutions covering the search space and a collection of high-performing solutions for each distinct reward area. We evaluate SERENE on various sparse reward environments and show it compares favorably to existing baselines.
We present in this paper an exertion of our previous work by increasing the robustness and coverage of the evolution search via hybridisation with a state-of-the-art novelty search and accelerate the individual agent behaviour searches via a novel be
haviour-component sharing technique. Via these improvements, we present Swarm Learning Classifier System 2.0 (SLCS2), a behaviour evolving algorithm which is robust to complex environments, and seen to out-perform a human behaviour designer in challenging cases of the data-transfer task in a range of environmental conditions. Additionally, we examine the impact of tailoring the SLCS2 rule generator for specific environmental conditions. We find this leads to over-fitting, as might be expected, and thus conclude that for greatest environment flexibility a general rule generator should be utilised.
We present a neural architecture search algorithm to construct compact reinforcement learning (RL) policies, by combining ENAS and ES in a highly scalable and intuitive way. By defining the combinatorial search space of NAS to be the set of different
edge-partitionings (colorings) into same-weight classes, we represent compact architectures via efficient learned edge-partitionings. For several RL tasks, we manage to learn colorings translating to effective policies parameterized by as few as $17$ weight parameters, providing >90% compression over vanilla policies and 6x compression over state-of-the-art compact policies based on Toeplitz matrices, while still maintaining good reward. We believe that our work is one of the first attempts to propose a rigorous approach to training structured neural network architectures for RL problems that are of interest especially in mobile robotics with limited storage and computational resources.
Different subsystems of organisms adapt over many time scales, such as rapid changes in the nervous system (learning), slower morphological and neurological change over the lifetime of the organism (postnatal development), and change over many genera
tions (evolution). Much work has focused on instantiating learning or evolution in robots, but relatively little on development. Although many theories have been forwarded as to how development can aid evolution, it is difficult to isolate each such proposed mechanism. Thus, here we introduce a minimal yet embodied model of development: the body of the robot changes over its lifetime, yet growth is not influenced by the environment. We show that even this simple developmental model confers evolvability because it allows evolution to sweep over a larger range of body plans than an equivalent non-developmental system, and subsequent heterochronic mutations lock in this body plan in more morphologically-static descendants. Future work will involve gradually complexifying the developmental model to determine when and how such added complexity increases evolvability.
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.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
