Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter space with deterministic behavioral policies. The resulting objective is amenable to standard neural network optimization strategies like stochastic gradient descent or stochastic gradient Hamiltonian Monte Carlo. Incorporation of previous rollouts via importance sampling greatly improves data-efficiency, whilst stochastic optimization schemes facilitate the escape from local optima. We evaluate the proposed approach on a series of continuous control benchmark tasks. The results show that the proposed algorithm is able to successfully and reliably learn solutions using fewer system interactions than standard policy gradient methods.
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a policy prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off. When the policy prior has control-theoretic stability guarantees, we further show that this regularization approximately preserves those stability guarantees throughout learning. We validate our approach empirically on a range of settings, and demonstrate significantly reduced variance, guaranteed dynamic stability, and more efficient learning than deep RL alone.
Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of hyperparameters. One reason is that most approaches use a noisy version of their operating policy to explore - thereby limiting the range of exploration. In this paper, we introduce Collaborative Evolutionary Reinforcement Learning (CERL), a scalable framework that comprises a portfolio of policies that simultaneously explore and exploit diverse regions of the solution space. A collection of learners - typically proven algorithms like TD3 - optimize over varying time-horizons leading to this diverse portfolio. All learners contribute to and use a shared replay buffer to achieve greater sample efficiency. Computational resources are dynamically distributed to favor the best learners as a form of online algorithm selection. Neuroevolution binds this entire process to generate a single emergent learner that exceeds the capabilities of any individual learner. Experiments in a range of continuous control benchmarks demonstrate that the emergent learner significantly outperforms its composite learners while remaining overall more sample-efficient - notably solving the Mujoco Humanoid benchmark where all of its composite learners (TD3) fail entirely in isolation.
Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted. Gaussian exploration however does not result in smooth trajectories that generally correspond to safe and rewarding behaviors in practical tasks. In addition, Gaussian policies do not result in an effective exploration of an environment and become increasingly inefficient as the action rate increases. This contributes to a low sample efficiency often observed in learning continuous control tasks. We introduce a family of stationary autoregressive (AR) stochastic processes to facilitate exploration in continuous control domains. We show that proposed processes possess two desirable features: subsequent process observations are temporally coherent with continuously adjustable degree of coherence, and the process stationary distribution is standard normal. We derive an autoregressive policy (ARP) that implements such processes maintaining the standard agent-environment interface. We show how ARPs can be easily used with the existing off-the-shelf learning algorithms. Empirically we demonstrate that using ARPs results in improved exploration and sample efficiency in both simulated and real world domains, and, furthermore, provides smooth exploration trajectories that enable safe operation of robotic hardware.
Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge.
Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to develop these ideas are either researchers' limited codebase or proprietary closed systems. We present Marathon Environments, a suite of open source, continuous control benchmarks implemented on the Unity game engine, using the Unity ML- Agents Toolkit. We demonstrate through these benchmarks that continuous control research is transferable to a commercial game engine. Furthermore, we exhibit the robustness of these environments by reproducing advanced continuous control research, such as learning to walk, run and backflip from motion capture data; learning to navigate complex terrains; and by implementing a video game input control system. We show further robustness by training with alternative algorithms found in OpenAI.Baselines. Finally, we share strategies for significantly reducing the training time.
Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while maintaining a low UTD ratio of 1. Notably, CrossQ does not rely on advanced bias-reduction schemes used in current methods. CrossQ's contributions are threefold: (1) it matches or surpasses current state-of-the-art methods in terms of sample efficiency, (2) it substantially reduces the computational cost compared to REDQ and DroQ, (3) it is easy to implement, requiring just a few lines of code on top of SAC.
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifies writing data-parallel and model-parallel research code. The same models can be effortlessly deployed to different cluster architectures (i.e. one or many machines containing CPUs, GPUs or TPU accelerators) using synchronous or asynchronous training regimes. To demonstrate the generality and scalability of TF-Replicator, we implement and benchmark three very different models: (1) A ResNet-50 for ImageNet classification, (2) a SN-GAN for class-conditional ImageNet image generation, and (3) a D4PG reinforcement learning agent for continuous control. Our results show strong scalability performance without demanding any distributed systems expertise of the user. The TF-Replicator programming model will be open-sourced as part of TensorFlow 2.0 (see https://github.com/tensorflow/community/pull/25).
Black-box optimizers that explore in parameter space have often been shown to outperform more sophisticated action space exploration methods developed specifically for the reinforcement learning problem. We examine these black-box methods closely to identify situations in which they are worse than action space exploration methods and those in which they are superior. Through simple theoretical analyses, we prove that complexity of exploration in parameter space depends on the dimensionality of parameter space, while complexity of exploration in action space depends on both the dimensionality of action space and horizon length. This is also demonstrated empirically by comparing simple exploration methods on several model problems, including Contextual Bandit, Linear Regression and Reinforcement Learning in continuous control.
In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductive bias that encodes the natural ordering between discrete actions. This ordinal architecture further significantly improves the performance of PPO/TRPO.
Recurrent neural networks (RNNs) for reinforcement learning (RL) have shown distinct advantages, e.g., solving memory-dependent tasks and meta-learning. However, little effort has been spent on improving RNN architectures and on understanding the underlying neural mechanisms for performance gain. In this paper, we propose a novel, multiple-timescale, stochastic RNN for RL. Empirical results show that the network can autonomously learn to abstract sub-goals and can self-develop an action hierarchy using internal dynamics in a challenging continuous control task. Furthermore, we show that the self-developed compositionality of the network enhances faster re-learning when adapting to a new task that is a re-composition of previously learned sub-goals, than when starting from scratch. We also found that improved performance can be achieved when neural activities are subject to stochastic rather than deterministic dynamics.
A policy is said to be robust if it maximizes the reward while considering a bad, or even adversarial, model. In this work we formalize two new criteria of robustness to action uncertainty. Specifically, we consider two scenarios in which the agent attempts to perform an action $a$, and (i) with probability $\alpha$, an alternative adversarial action $\bar a$ is taken, or (ii) an adversary adds a perturbation to the selected action in the case of continuous action space. We show that our criteria are related to common forms of uncertainty in robotics domains, such as the occurrence of abrupt forces, and suggest algorithms in the tabular case. Building on the suggested algorithms, we generalize our approach to deep reinforcement learning (DRL) and provide extensive experiments in the various MuJoCo domains. Our experiments show that not only does our approach produce robust policies, but it also improves the performance in the absence of perturbations. This generalization indicates that action-robustness can be thought of as implicit regularization in RL problems.
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many benefits, such as ability to evaluate each resulting policy. However, they usually discard all the information about the policies which existed before. In this work, we propose adaptation of the replay buffer concept, borrowed from the off-policy learning setting, to create the method, combining advantages of on- and off-policy learning. To achieve this, the proposed algorithm generalises the $Q$-, value and advantage functions for data from multiple policies. The method uses trust region optimisation, while avoiding some of the common problems of the algorithms such as TRPO or ACKTR: it uses hyperparameters to replace the trust region selection heuristics, as well as the trainable covariance matrix instead of the fixed one. In many cases, the method not only improves the results comparing to the state-of-the-art trust region on-policy learning algorithms such as PPO, ACKTR and TRPO, but also with respect to their off-policy counterpart DDPG.
Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task. In this paper, we propose an HRL method that learns a latent variable of a hierarchical policy using mutual information maximization. Our approach can be interpreted as a way to learn a discrete and latent representation of the state-action space. To learn option policies that correspond to modes of the advantage function, we introduce advantage-weighted importance sampling. In our HRL method, the gating policy learns to select option policies based on an option-value function, and these option policies are optimized based on the deterministic policy gradient method. This framework is derived by leveraging the analogy between a monolithic policy in standard RL and a hierarchical policy in HRL by using a deterministic option policy. Experimental results indicate that our HRL approach can learn a diversity of options and that it can enhance the performance of RL in continuous control tasks.
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. We present the first continuous control deep reinforcement learning algorithm which can learn effectively from arbitrary, fixed batch data, and empirically demonstrate the quality of its behavior in several tasks.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, and show that it can find correct task boundaries and event encodings in an unsupervised manner. Latent codes and associated behavior policies discovered by CompILE can be used by a hierarchical agent, where the high-level policy selects actions in the latent code space, and the low-level, task-specific policies are simply the learned decoders. We found that our CompILE-based agent could learn given only sparse rewards, where agents without task-specific policies struggle.
We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies . Our skills are multi-goal policies learned in isolation in simpler environments using existing multigoal RL formulations, analogous to options or macroactions. Coarse skill dynamics, i.e., the state transition caused by a (complete) skill execution, are learnt and are unrolled forward during lookahead search. Policy search benefits from temporal abstraction during exploration, though itself operates over low-level primitive actions, and thus the resulting policies does not suffer from suboptimality and inflexibility caused by coarse skill chaining. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parametrized skills as building blocks of the policy itself, as opposed to guiding exploration. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parameterized skills as building blocks of the policy itself, as opposed to guiding exploration.
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this using a latent dynamics model with both deterministic and stochastic transition components. Moreover, we propose a multi-step variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards, which exceed the difficulty of tasks that were previously solved by planning with learned models. PlaNet uses substantially fewer episodes and reaches final performance close to and sometimes higher than strong model-free algorithms.
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the agent should go during execution and where it should stop, and uses the predicted distributions to select the actions to execute. This two-step model decomposition allows for simple and efficient training using a combination of supervised learning and imitation learning. We evaluate our approach with a realistic drone simulator, and demonstrate absolute task-completion accuracy improvements of 16.85% over two state-of-the-art instruction-following methods.
In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic. Besides the ensemble perspective, we also formulate ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options. Furthermore, we perform a look-ahead tree search with those actors and a learned value prediction model, resulting in a refined value estimation. We demonstrate a significant performance boost of ACE over DDPG and its variants in challenging physical robot simulators.