Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In addition, most reinforcement learning research on multi-task learning has been focused on discrete action spaces, which are not used for robotic control in the real-world. In this work, we apply multi-task learning methods to continuous action spaces and benchmark their performance on a series of simulated continuous control tasks. Most notably, we show that multi-task learning outperforms our baselines and alternative knowledge sharing methods.
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 across different classes of terrain. We also introduce an input injection method for augmenting an existing policy network to exploit new input features. Lastly, our method uses transfer learning to assist in the efficient acquisition of new skills. The combination of these methods allows a policy to be incrementally augmented with new skills. We compare our progressive learning and integration via distillation (PLAID) method against three alternative baselines.
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) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such as Q-learning. A limiting factor in classic model-free RL is that the learning signal consists only of scalar rewards, ignoring much of the rich information contained in state transition tuples. Model-based RL uses this information, by training a predictive model, but often does not achieve the same asymptotic performance as model-free RL due to model bias. We introduce temporal difference models (TDMs), a family of goal-conditioned value functions that can be trained with model-free learning and used for model-based control. TDMs combine the benefits of model-free and model-based RL: they leverage the rich information in state transitions to learn very efficiently, while still attaining asymptotic performance that exceeds that of direct model-based RL methods. Our experimental results show that, on a range of continuous control tasks, TDMs provide a substantial improvement in efficiency compared to state-of-the-art model-based and model-free methods.
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Our method, which builds on top of Deep Deterministic Policy Gradients and Hindsight Experience Replay, provides an order of magnitude of speedup over RL on simulated robotics tasks. It is simple to implement and makes only the additional assumption that we can collect a small set of demonstrations. Furthermore, our method is able to solve tasks not solvable by either RL or behavior cloning alone, and often ends up outperforming the demonstrator policy.
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics models within a model-free reinforcement learning algorithm, we improve value estimation, which, in turn, reduces the sample complexity of learning.
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.
Reinforcement Learning and the Evolutionary Strategy are two major approaches in addressing complicated control problems. Both are strong contenders and have their own devotee communities. Both groups have been very active in developing new advances in their own domain and devising, in recent years, leading-edge techniques to address complex continuous control tasks. Here, in the context of Deep Reinforcement Learning, we formulate a parallelized version of the Proximal Policy Optimization method and a Deep Deterministic Policy Gradient method. Moreover, we conduct a thorough comparison between the state-of-the-art techniques in both camps fro continuous control; evolutionary methods and Deep Reinforcement Learning methods. The results show there is no consistent winner.
We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally across a set of similar environments, each with dynamics drawn from a prior distribution. We propose that the agent is able to adjust its actions almost immediately, based on small set of observations. This robust and adaptive behavior is enabled by using a policy gradient algorithm with an Long Short Term Memory (LSTM) function approximation. Finally, we train an agent to navigate a two-dimensional environment with uncertain dynamics and noisy observations. We demonstrate that this agent has good zero-shot performance in a real physical environment. Our preliminary results indicate that the agent is able to infer the environmental dynamics after only a few timesteps, and adjust its actions accordingly.
The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input. The second part of the paper presents a set of concrete research ideas for improving RL algorithms, most of which are related to Multi-Goal RL and Hindsight Experience Replay.
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recently introduced Black-DROPS algorithm exploits a black-box optimization algorithm to achieve both high data-efficiency and good computation times when several cores are used; nevertheless, like all model-based policy search approaches, Black-DROPS does not scale to high dimensional state/action spaces. In this paper, we introduce a new model learning procedure in Black-DROPS that leverages parameterized black-box priors to (1) scale up to high-dimensional systems, and (2) be robust to large inaccuracies of the prior information. We demonstrate the effectiveness of our approach with the "pendubot" swing-up task in simulation and with a physical hexapod robot (48D state space, 18D action space) that has to walk forward as fast as possible. The results show that our new algorithm is more data-efficient than previous model-based policy search algorithms (with and without priors) and that it can allow a physical 6-legged robot to learn new gaits in only 16 to 30 seconds of interaction time.
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.
This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks. The performance of these trained policies are competitive with state of the art results, obtained with more elaborate parameterizations such as fully connected neural networks. Furthermore, existing training and testing scenarios are shown to be very limited and prone to over-fitting, thus giving rise to only trajectory-centric policies. Training with a diverse initial state distribution is shown to produce more global policies with better generalization. This allows for interactive control scenarios where the system recovers from large on-line perturbations; as shown in the supplementary video.
Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stochastic variance reduced gradient descent (SVRG) to model-free policy gradient to significantly improve the sample-efficiency. The SVRG estimation is incorporated into a trust-region Newton conjugate gradient framework for the policy optimization. On several Mujoco tasks, our method achieves significantly better performance compared to the state-of-the-art model-free policy gradient methods in robotic continuous control such as trust region policy optimization (TRPO)
All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient methods or $\epsilon$-greedy in Q-learning. While these methods are appealing due to their simplicity, they do not explore the state space in a methodical manner. We present an approach that uses a model to derive reward bonuses as a means of intrinsic motivation to improve model-free reinforcement learning. A key insight of our approach is that this dynamics model can be learned in the latent feature space of a value function, representing the dynamics of the agent and the environment. This method is both theoretically grounded and computationally advantageous, permitting the efficient use of Bayesian information-theoretic methods in high-dimensional state spaces. We evaluate our method on several continuous control tasks, focusing on improving exploration.
Model-free approaches for reinforcement learning (RL) and continuous control find policies based only on past states and rewards, without fitting a model of the system dynamics. They are appealing as they are general purpose and easy to implement; however, they also come with fewer theoretical guarantees than model-based RL. In this work, we present a new model-free algorithm for controlling linear quadratic (LQ) systems, and show that its regret scales as $O(T^{\xi+2/3})$ for any small $\xi>0$ if time horizon satisfies $T>C^{1/\xi}$ for a constant $C$. The algorithm is based on a reduction of control of Markov decision processes to an expert prediction problem. In practice, it corresponds to a variant of policy iteration with forced exploration, where the policy in each phase is greedy with respect to the average of all previous value functions. This is the first model-free algorithm for adaptive control of LQ systems that provably achieves sublinear regret and has a polynomial computation cost. Empirically, our algorithm dramatically outperforms standard policy iteration, but performs worse than a model-based approach.
This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we call the Distributed Distributional Deep Deterministic Policy Gradient algorithm, D4PG. We also combine this technique with a number of additional, simple improvements such as the use of $N$-step returns and prioritized experience replay. Experimentally we examine the contribution of each of these individual components, and show how they interact, as well as their combined contributions. Our results show that across a wide variety of simple control tasks, difficult manipulation tasks, and a set of hard obstacle-based locomotion tasks the D4PG algorithm achieves state of the art performance.