Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous control, general variance in the algorithms, and reproducibility of reported results. We provide guidelines on reporting novel results as comparisons against baseline methods such that future researchers can make informed decisions when investigating novel methods.
In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also a method that learns non-trivial tasks in continuous control as well as discrete control policies directly from raw pixel inputs. We tested our approach across discrete domains in Atari games as well as continuous domains in the MuJoCo environment. With the proposed methods, we are able to achieve higher rewards and a 2- to 3-fold improvement in sample efficiency on average, compared to previous state-of-the-art on-policy actor-critic methods. Code is available at https://github.com/openai/baselines
Discrete-action algorithms have been central to numerous recent successes of deep reinforcement learning. However, applying these algorithms to high-dimensional action tasks requires tackling the combinatorial increase of the number of possible actions with the number of action dimensions. This problem is further exacerbated for continuous-action tasks that require fine control of actions via discretization. In this paper, we propose a novel neural architecture featuring a shared decision module followed by several network branches, one for each action dimension. This approach achieves a linear increase of the number of network outputs with the number of degrees of freedom by allowing a level of independence for each individual action dimension. To illustrate the approach, we present a novel agent, called Branching Dueling Q-Network (BDQ), as a branching variant of the Dueling Double Deep Q-Network (Dueling DDQN). We evaluate the performance of our agent on a set of challenging continuous control tasks. The empirical results show that the proposed agent scales gracefully to environments with increasing action dimensionality and indicate the significance of the shared decision module in coordination of the distributed action branches. Furthermore, we show that the proposed agent performs competitively against a state-of-the-art continuous control algorithm, Deep Deterministic Policy Gradient (DDPG).
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning.
Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by fitting the value function with a Bayesian Neural Network. We optimize an $\alpha$-divergence objective with Bayesian dropout approximation to learn and estimate this distribution. We show that using the Monte Carlo posterior mean of the Bayesian value function distribution, rather than a deterministic network, improves stability and performance of policy gradient methods in continuous control MuJoCo simulations.
The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine, making them easy to use and modify. We include benchmarks for several learning algorithms. The Control Suite is publicly available at https://www.github.com/deepmind/dm_control . A video summary of all tasks is available at http://youtu.be/rAai4QzcYbs .
Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation. We prove that our estimator, named clipped action policy gradient (CAPG), is unbiased and achieves lower variance than the conventional estimator that ignores action bounds. Experimental results demonstrate that CAPG generally outperforms the conventional estimator, indicating that it is a better policy gradient estimator for continuous control tasks. The source code is available at https://github.com/pfnet-research/capg.
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GAC). GAC firstly learns a guide actor that locally maximizes the critic and then it updates the policy parameter based on the guide actor by supervised learning. Our main theoretical contributions are two folds. First, we show that GAC updates the guide actor by performing second-order optimization in the action space where the curvature matrix is based on the Hessians of the critic. Second, we show that the deterministic policy gradient method is a special case of GAC when the Hessians are ignored. Through experiments, we show that our method is a promising reinforcement learning method for continuous controls.
Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically require a prohibitively large amount of on-policy interaction with the environment. To address this problem, we propose an off-policy trust region method, Trust-PCL. The algorithm is the result of observing that the optimal policy and state values of a maximum reward objective with a relative-entropy regularizer satisfy a set of multi-step pathwise consistencies along any path. Thus, Trust-PCL is able to maintain optimization stability while exploiting off-policy data to improve sample efficiency. When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.
Model-free reinforcement learning (RL) methods are succeeding in a growing number of tasks, aided by recent advances in deep learning. However, they tend to suffer from high sample complexity, which hinders their use in real-world domains. Alternatively, model-based reinforcement learning promises to reduce sample complexity, but tends to require careful tuning and to date have succeeded mainly in restrictive domains where simple models are sufficient for learning. In this paper, we analyze the behavior of vanilla model-based reinforcement learning methods when deep neural networks are used to learn both the model and the policy, and show that the learned policy tends to exploit regions where insufficient data is available for the model to be learned, causing instability in training. To overcome this issue, we propose to use an ensemble of models to maintain the model uncertainty and regularize the learning process. We further show that the use of likelihood ratio derivatives yields much more stable learning than backpropagation through time. Altogether, our approach Model-Ensemble Trust-Region Policy Optimization (ME-TRPO) significantly reduces the sample complexity compared to model-free deep RL methods on challenging continuous control benchmark tasks.
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such beliefs by introducing a random search method for training static, linear policies for continuous control problems, matching state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks. Our method also finds a nearly optimal controller for a challenging instance of the Linear Quadratic Regulator, a classical problem in control theory, when the dynamics are not known. Computationally, our random search algorithm is at least 15 times more efficient than the fastest competing model-free methods on these benchmarks. We take advantage of this computational efficiency to evaluate the performance of our method over hundreds of random seeds and many different hyperparameter configurations for each benchmark task. Our simulations highlight a high variability in performance in these benchmark tasks, suggesting that commonly used estimations of sample efficiency do not adequately evaluate the performance of RL algorithms.
Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework to reduce the variance. To invoke RB, our proposed algorithm (POSA) learns the underlying factorization structure among the action space based on the second-order advantage information. POSA captures the quadratic information explicitly and efficiently by utilizing the wide & deep architecture. Empirical studies show that our proposed approach demonstrates the performance improvements on high-dimensional synthetic settings and OpenAI Gym's MuJoCo continuous control tasks.
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely sensitive to hyperparameters. Collectively, these challenges severely limit the applicability of these approaches to real-world problems. Evolutionary Algorithms (EAs), a class of black box optimization techniques inspired by natural evolution, are well suited to address each of these three challenges. However, EAs typically suffer from high sample complexity and struggle to solve problems that require optimization of a large number of parameters. In this paper, we introduce Evolutionary Reinforcement Learning (ERL), a hybrid algorithm that leverages the population of an EA to provide diversified data to train an RL agent, and reinserts the RL agent into the EA population periodically to inject gradient information into the EA. ERL inherits EA's ability of temporal credit assignment with a fitness metric, effective exploration with a diverse set of policies, and stability of a population-based approach and complements it with off-policy DRL's ability to leverage gradients for higher sample efficiency and faster learning. Experiments in a range of challenging continuous control benchmarks demonstrate that ERL significantly outperforms prior DRL and EA methods.
Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter. Such problems are naturally solved using policy based reinforcement learning (RL) methods, but unfortunately these often suffer from high variance leading to instability and slow convergence. Unnecessary variance is introduced whenever policies over bounded action spaces are modeled using distributions with unbounded support by applying a transformation $T$ to the sampled action before execution in the environment. Recently, the variance reduced clipped action policy gradient (CAPG) was introduced for actions in bounded intervals, but to date no variance reduced methods exist when the action is a direction, something often seen in RTS games. To this end we introduce the angular policy gradient (APG), a stochastic policy gradient method for directional control. With the marginal policy gradients family of estimators we present a unified analysis of the variance reduction properties of APG and CAPG; our results provide a stronger guarantee than existing analyses for CAPG. Experimental results on a popular RTS game and a navigation task show that the APG estimator offers a substantial improvement over the standard policy gradient.
Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation, goal-directed tasks whose natural reward function is sparse remain intractable for state-of-the-art model-free algorithms for continuous control. The bottleneck in these tasks is the prohibitive amount of exploration required to obtain a learning signal from the initial state of the system. In this work, we leverage physical priors in the form of an approximate system dynamics model to design a curriculum scheme for a model-free policy optimization algorithm. Our Backward Reachability Curriculum (BaRC) begins policy training from states that require a small number of actions to accomplish the task, and expands the initial state distribution backwards in a dynamically-consistent manner once the policy optimization algorithm demonstrates sufficient performance. BaRC is general, in that it can accelerate training of any model-free RL algorithm on a broad class of goal-directed continuous control MDPs. Its curriculum strategy is physically intuitive, easy-to-tune, and allows incorporating physical priors to accelerate training without hindering the performance, flexibility, and applicability of the model-free RL algorithm. We evaluate our approach on two representative dynamic robotic learning problems and find substantial performance improvement relative to previous curriculum generation techniques and naive exploration strategies.
Diffusion 모델은 비전, 언어, 강화학습에서 효과적인 분포 추정기로 부상했지만, 하위 과제에서 사전분포로 쓰일 때 다루기 어려운(intractable) 사후 추론 문제를 야기한다. 본 논문은 diffusion 생성 모델 사전분포 $p(\mathbf{x})$와 블랙박스 제약 또는 가능도 함수 $r(\mathbf{x})$로 이루어진 모델에서, 데이터에 대한 사후분포 $\mathbf{x}\sim p^{\rm post}(\mathbf{x})\propto p(\mathbf{x})r(\mathbf{x})$의 상각화(amortized) 샘플링을 연구한다. 이 사후분포에서 샘플링하는 diffusion 모델을 학습하기 위한 데이터 없는(data-free) 학습 목적 함수인 relative trajectory balance의 점근적 정확성을 진술하고 증명하며, 이 문제는 기존 방법이 근사적으로만 또는 제한된 경우에만 다룰 수 있다. Relative trajectory balance는 diffusion 모델에 대한 generative flow network 관점에서 나오며, 모드 커버리지(mode coverage) 개선을 위해 deep 강화학습 기법을 활용할 수 있게 한다. 실험은 diffusion 사전분포 하에서 임의의 사후분포에 대한 편향 없는(unbiased) 추론의 넓은 가능성을 보여 준다: 비전(classifier guidance), 언어(이산 diffusion LLM 하 infilling), 다중모달 데이터(text-to-image 생성). 생성 모델링을 넘어 score 기반 행동 사전분포를 갖는 연속 제어 문제에 relative trajectory balance를 적용하여 오프라인 강화학습 벤치마크에서 최신(state-of-the-art) 결과를 달성한다.
기존의 불확실성 인식 시간차(TD) 학습은 TD 오차를 영평균(zero-mean) 가우시안으로 모델링하는 경우가 많다. 이 가정은 부트스트래핑과 탐험(exploration)으로 인해 발생하는 heavy-tailed 및 이분산(heteroscedastic) 잔차를 놓칠 수 있다. 우리는 일반화 가우시안 분포(GGD)에 기반한 상태 조건부 형상(shape) 헤드를 도입하고, 수치적으로 수정된 GGD 손실(loss)을 비정상(nonstationary) TD 잔차에 대한 온라인 대리(surrogate)로 사용한다. 때로 혼동되는 두 가지 수학적 사실을 구분한다: 정확한 GGD 가능도(likelihood)는 모든 $β>0$에 대해 정규화되어 있지만, 그 지수 밀도 커널(kernel)은 $β\in(0,2]$에서 양의 정부(positive definite)이다. 학습된 형상을 이용해 단순한 단조 가중 휴리스틱을 구성하고, 앙상블(ensemble) TD 오차의 분산과 표본 초과 첨도(sample excess kurtosis)로부터 Batch Inverse Error Variance(BIEV) 정규화(regularization)를 제안한다. 연속 및 이산 제어 벤치마크(benchmark) 전반에서 형상 인식 변형이 여러 설정에서 가우시안 기반 변형보다 개선되지만, 이득은 과제와 체제(regime)에 따라 달라진다.
시간적 추상화(temporal abstraction)는 강화학습 에이전트가 서로 다른 시간 척도에 걸쳐 지식을 표현하고 전략을 수립할 수 있게 한다. Option-critic 프레임워크는 모델 없는(model-free) 설정에서 옵션(options)으로 표현되는 시간적으로 확장된 행동을 종단간(end-to-end) 학습할 수 있음이 입증되었다. 그러나 option-critic의 실용 가능성은 두 가지 주요 난제로 인해 여전히 제한적이다: 여러 옵션이 매우 유사한 행동을 채택하는 경우, 또는 과제 관련 옵션 집합이 줄어드는 경우. 이러한 현상은 시간적 추상화의 필요성을 무효화할 뿐만 아니라 성능에도 영향을 미친다. 본 논문에서는 다양한 옵션 집합을 학습함으로써 이 문제들을 해결한다. 우리는 옵션 집합 내 행동 다양성을 촉진하기 위해 과제 보상을 보강하는 정보 이론적 내재 보상(intrinsic reward)과 새로운 종료 목적 함수를 제안한다. 우리는 제안 방법이 여러 이산 및 연속 제어 과제에서 옵션을 종단간 학습할 수 있으며, option-critic을 큰 마진으로 능가함을 실증적으로 보인다. 또한 우리는 option-critic과 달리 제안 접근법이 견고하고, 재사용 가능하며, 신뢰할 수 있고 해석 가능한 옵션을 지속적으로 생성함을 보인다.