This paper aims to explore the potential of combining Deep Reinforcement Learning (DRL) with Knowledge Distillation (KD) by distilling various DRL algorithms and studying their distillation effects. By doing so, the computational burden of deep models could be reduced while maintaining the performance. The primary objective is to provide a benchmark for evaluating the performance of different DRL algorithms that have been refined using KD techniques. By distilling these algorithms, the goal is to develop efficient and fast DRL models. This research is expected to provide valuable insights that can facilitate further advancements in this promising direction. By exploring the combination of DRL and KD, this work aims to promote the development of models that require fewer GPU resources, learn more quickly, and make faster decisions in complex environments. The results of this research have the capacity to significantly advance the field of DRL and pave the way for the future deployment of resource-efficient, decision-making intelligent systems.
National Tsing Hua University（国立清华大学）；Preferred Networks（优选网络）
Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the course of training enables faster policy improvement for an RL agent. Motivated by these recent insights, we propose Periodic Intra-Ensemble Knowledge Distillation (PIEKD). PIEKD is a learning framework that uses an ensemble of policies to act in the environment while periodically sharing knowledge amongst policies in the ensemble through knowledge distillatio…
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction problem. A dataset of learning histories is generated by a source RL algorithm, and then a causal transformer is trained by autoregressively predicting actions given their preceding learning histories as context. Unlike sequential policy prediction architectures that distill post-learning or expert sequ…
Yonsei University（延世大学）；Deakin University（迪肯大学）；Samsung Electronics Co., Ltd.（三星电子株式会社）；University of Oulu（奥卢大学）
Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent. Since the RM contains all state observations and action policy history, it may incur huge communication overhead while violating the privacy of each agent. Alternatively, this article presents a communication-efficient and privacy-preserving distributed RL framework, coined federated reinforcement distillation (FRD). In FRD, each agent exchanges its proxy experience replay memory (ProxRM), in which policies are locally averaged with respect to proxy states clu…
University of South Carolina（南卡罗来纳大学）；San Francisco State University（旧金山州立大学）
Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is underexplored in deep reinforcement learning, and existing approaches are computationally inefficient, resulting in a long distillation time. In addition, the effectiveness of the distillation process is still limited to the model capacity. We propose a new distillation mechanism, called real-time policy distillation, in which training the teacher model and…
Tsinghua University（清华大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general reinforcement learning paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance. In this paper, we present IQ, i.e., interference-aware deep Q-learning, to mitigate catastrophic inter…
ISAE-SUPAERO, Université de Toulouse（图卢兹大学高等航空航天学院）；Sandbox AQ（Sandbox AQ公司）
Learning a good state representation is a critical skill when dealing with multiple tasks in Reinforcement Learning as it allows for transfer and better generalization between tasks. However, defining what constitute a useful representation is far from simple and there is so far no standard method to find such an encoding. In this paper, we argue that distillation -- a process that aims at imitating a set of given policies with a single neural network -- can be used to learn a state representation displaying favorable characteristics. In this regard, we define three criteria that measure desir…
Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase performance, but do not generally look at how information can be shared between agents to address the curse of dimensionality in MARL. We posit that a multiagent problem can be decomposed into a multi-task problem where each agent explores a subset of the state space instead of explorin…
Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning
University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；University of Central Florida（中佛罗里达大学）；Air Force Research Laboratory（空军研究实验室）；Florida International University（佛罗里达国际大学）；University of Colorado（科罗拉多大学）
ENSTA Paris（巴黎高等先进技术学院）；Institute Polytechnique de Paris（巴黎理工学院）；INRIA（法国国家信息与自动化研究所）；Softbank Robotics Europe（软银机器人欧洲公司）；Thales（泰雷兹集团）
In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-…
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access to a human expert, and learning from intermediate forms of supervision (like binary preferences) is time-consuming and extracts little information from each human intervention. Can we overcome these challenges by building agents that learn from rich, interactive feedback instead? We propose a new supervision paradigm for interactive learning based on "teacha…
In reinforcement learning, domain randomisation is an increasingly popular technique for learning more general policies that are robust to domain-shifts at deployment. However, naively aggregating information from randomised domains may lead to high variance in gradient estimation and unstable learning process. To address this issue, we present a peer-to-peer online distillation strategy for RL termed P2PDRL, where multiple workers are each assigned to a different environment, and exchange knowledge through mutual regularisation based on Kullback-Leibler divergence. Our experiments on continuo…
ISAE-SUPAERO, Université de Toulouse（图卢兹大学高等航空航天学院）；Sandbox AQ（Sandbox AQ公司）
Although transfer learning is considered to be a milestone in deep reinforcement learning, the mechanisms behind it are still poorly understood. In particular, predicting if knowledge can be transferred between two given tasks is still an unresolved problem. In this work, we explore the use of network distillation as a feature extraction method to better understand the context in which transfer can occur. Notably, we show that distillation does not prevent knowledge transfer, including when transferring from multiple tasks to a new one, and we compare these results with transfer without prior …
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone…
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
UCL Dept. of Statistical Science（伦敦大学学院统计科学系）；UCL Centre for AI（伦敦大学学院人工智能中心）；Alibaba Group（阿里巴巴集团）；Dept. of EEE（电子工程系）；Imperial College London（伦敦帝国理工学院）；UNIST（全南大学）；University of Basel（巴塞尔大学）
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone…
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each individual skill is a specialist in a specific skill and its associated state distribution. We extend policy distillation methods to the continuous action setting and leverage this technique to combine expert policies, as evaluated in the domain of simulated bipedal locomotion a…
University of Maryland（马里兰大学）；National Institute for Standards and Technology（美国国家标准与技术研究院）
We present Multiple Scenario Verifiable Reinforcement Learning via Policy Extraction (MSVIPER), a new method for policy distillation to decision trees for improved robot navigation. MSVIPER learns an "expert" policy using any Reinforcement Learning (RL) technique involving learning a state-action mapping and then uses imitation learning to learn a decision-tree policy from it. We demonstrate that MSVIPER results in efficient decision trees and can accurately mimic the behavior of the expert policy. Moreover, we present efficient policy distillation and tree-modification techniques that take ad…
Double Distillation Network for Multi-Agent Reinforcement Learning
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Automation Engineering, University of Electronic Science and Technology of China（电子科技大学自动化工程学院）
Cambridge, United Kingdom（英国剑桥）；Cape Town, South Africa（南非开普敦）
This paper demonstrates the application of reinforcement learning (RL) to process synthesis by presenting Distillation Gym, a set of RL environments in which an RL agent is tasked with designing a distillation train, given a user defined multi-component feed stream. Distillation Gym interfaces with a process simulator (COCO and ChemSep) to simulate the environment. A demonstration of two distillation problem examples are discussed in this paper (a Benzene, Toluene, P-xylene separation problem and a hydrocarbon separation problem), in which a deep RL agent is successfully able to learn within D…
In this paper, we describe NeurIPS 2019 Learning to Move - Walk Around challenge physics-based environment and present our solution to this competition which scored 1303.727 mean reward points and took 3rd place. Our method combines recent advances from both continuous- and discrete-action space reinforcement learning, such as Soft Actor-Critic and Recurrent Experience Replay in Distributed Reinforcement Learning. We trained our agent in two stages: to move somewhere at the first stage and to follow the target velocity field at the second stage. We also introduce novel Q-function split techniq…
Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These "actor-latency" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within …
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to comb…
In distributed reinforcement learning, it is common to exchange the experience memory of each agent and thereby collectively train their local models. The experience memory, however, contains all the preceding state observations and their corresponding policies of the host agent, which may violate the privacy of the agent. To avoid this problem, in this work, we propose a privacy-preserving distributed reinforcement learning (RL) framework, termed federated reinforcement distillation (FRD). The key idea is to exchange a proxy experience memory comprising a pre-arranged set of states and time-a…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed by reinforcement learning is indirect and may be computationally expensive. Recent generative adversarial methods based on matching the policy distribution between the expert and the agent could be unstable during training. We propose a new framework for imitation learning by estimating the support of the expert policy to compute a fixed reward function, whi…
Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands for highly coordinated environment exploration among all the participating agents. Many researchers attempted to cope with this challenge through learning centralized value functions. However, the common strategy for every agent to learn their local policies directly often fail to …
Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is computationally expensive. Moreover, the performance of the student model could be limited by the teacher model if the teacher model is not optimal. In the light of collaborative learning, we study the feasibility of involving joint intellectual efforts from diverse perspectives of student models. In this work, we introduce dual policy distillation(DPD), a student-s…
Huazhong University of Science and Technology（华中科技大学）；Zhejiang University（浙江大学）；Peking University（北京大学）；University of Arkansas, Fayetteville（阿肯色大学费耶特维尔分校）
Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly si…
