CALM: Conditional Adversarial Latent Models for Directable Virtual Characters

In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of movement that captures the complexity and diversity of human motion, and enables direct control over character movements. The approach jointly learns a control policy and a motion encoder that reconstructs key characteristics of a given motion without merely replicating it. The results show that CALM learns a semantic motion representation, enabling control over the generated motions and style-conditioning for higher-level task training. Once trained, the character can be controlled using intuitive interfaces, akin to those found in video games.

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs

Cloud datacenters are exponentially growing both in numbers and size. This increase results in a network activity surge that warrants better congestion avoidance. The resulting challenge is two-fold: (i) designing algorithms that can be custom-tuned to the complex traffic patterns of a given datacenter; but, at the same time (ii) run on low-level hardware with the required low latency of effective Congestion Control (CC). In this work, we present a Reinforcement Learning (RL) based CC solution that learns from certain traffic scenarios and successfully generalizes to others. We then distill the RL neural network policy into binary decision trees to achieve the desired $\mu$sec decision latency required for real-time inference with RDMA. We deploy the distilled policy on NVIDIA NICs in a real network and demonstrate state-of-the-art performance, balancing all tested metrics simultaneously: bandwidth, latency, fairness, and packet drops.

Towards Autonomous Grading In The Real World

In this work, we aim to tackle the problem of autonomous grading, where a dozer is required to flatten an uneven area. In addition, we explore methods for bridging the gap between a simulated environment and real scenarios. We design both a realistic physical simulation and a scaled real prototype environment mimicking the real dozer dynamics and sensory information. We establish heuristics and learning strategies in order to solve the problem. Through extensive experimentation, we show that although heuristics are capable of tackling the problem in a clean and noise-free simulated environment, they fail catastrophically when facing real world scenarios. As the heuristics are capable of successfully solving the task in the simulated environment, we show they can be leveraged to guide a learning agent which can generalize and solve the task both in simulation and in a scaled prototype environment.

Ensemble Bootstrapping for Q-Learning

Q-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by utilizing two estimators, yet results in an under-estimation bias. Similar to over-estimation in Q-learning, in certain scenarios, the under-estimation bias may degrade performance. In this work, we introduce a new bias-reduced algorithm called Ensemble Bootstrapped Q-Learning (EBQL), a natural extension of Double-Q-learning to ensembles. We analyze our method both theoretically and empirically. Theoretically, we prove that EBQL-like updates yield lower MSE when estimating the maximal mean of a set of independent random variables. Empirically, we show that there exist domains where both over and under-estimation result in sub-optimal performance. Finally, We demonstrate the superior performance of a deep RL variant of EBQL over other deep QL algorithms for a suite of ATARI games.

Reinforcement Learning for Datacenter Congestion Control

We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such learning-based algorithms have shown practical potential in this domain. Evidently, the most popular recent deployments rely on rule-based heuristics that are tested on a predetermined set of benchmarks. Consequently, these heuristics do not generalize well to newly-seen scenarios. Contrarily, we devise an RL-based algorithm with the aim of generalizing to different configurations of real-world datacenter networks. We overcome challenges such as partial-observability, non-stationarity, and multi-objectiveness. We further propose a policy gradient algorithm that leverages the analytical structure of the reward function to approximate its derivative and improve stability. We show that this scheme outperforms alternative popular RL approaches, and generalizes to scenarios that were not seen during training. Our experiments, conducted on a realistic simulator that emulates communication networks' behavior, exhibit improved performance concurrently on the multiple considered metrics compared to the popular algorithms deployed today in real datacenters. Our algorithm is being productized to replace heuristics in some of the largest datacenters in the world.

Maximizing the Total Reward via Reward Tweaking

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become unstable when the effective planning horizon is long, recent works refer to $\gamma$ as a hyper-parameter. In this work, we focus on the finite-horizon setting and introduce \emph{reward tweaking}. Reward tweaking learns a surrogate reward function $\tilde r$ for the discounted setting, which induces an optimal (undiscounted) return in the original finite-horizon task. Theoretically, we show that there exists a surrogate reward which leads to optimality in the original task and discuss the robustness of our approach. Additionally, we perform experiments in a high-dimensional continuous control task and show that reward tweaking guides the agent towards better long-horizon returns when it plans for short horizons using the tweaked reward.

Stabilizing Off-Policy Reinforcement Learning with Conservative Policy Gradients

In recent years, advances in deep learning have enabled the application of reinforcement learning algorithms in complex domains. However, they lack the theoretical guarantees which are present in the tabular setting and suffer from many stability and reproducibility problems \citep{henderson2018deep}. In this work, we suggest a simple approach for improving stability and providing probabilistic performance guarantees in off-policy actor-critic deep reinforcement learning regimes. Experiments on continuous action spaces, in the MuJoCo control suite, show that our proposed method reduces the variance of the process and improves the overall performance.

Natural Language State Representation for Reinforcement Learning

Recent advances in Reinforcement Learning have highlighted the difficulties in learning within complex high dimensional domains. We argue that one of the main reasons that current approaches do not perform well, is that the information is represented sub-optimally. A natural way to describe what we observe, is through natural language. In this paper, we implement a natural language state representation to learn and complete tasks. Our experiments suggest that natural language based agents are more robust, converge faster and perform better than vision based agents, showing the benefit of using natural language representations for Reinforcement Learning.

Inverse Reinforcement Learning in Contextual MDPs

We consider the Inverse Reinforcement Learning (IRL) problem in Contextual Markov Decision Processes (CMDPs). Here, the reward of the environment, which is not available to the agent, depends on a static parameter referred to as the context. Each context defines an MDP (with a different reward signal), and the agent is provided demonstrations by an expert, for different contexts. The goal is to learn a mapping from contexts to rewards, such that planning with respect to the induced reward will perform similarly to the expert, even for unseen contexts. We suggest two learning algorithms for this scenario. (1) For rewards that are a linear function of the context, we provide a method that is guaranteed to return an $\epsilon$-optimal solution after a polynomial number of demonstrations. (2) For general reward functions, we propose black-box descent methods based on evolutionary strategies capable of working with nonlinear estimators (e.g., neural networks). We evaluate our algorithms in autonomous driving and medical treatment simulations and demonstrate their ability to learn and generalize to unseen contexts.

Distributional Policy Optimization: An Alternative Approach for Continuous Control

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the action space and thus convergence to sub-optimal solutions. We suggest a novel distributional framework, able to represent arbitrary distribution functions over the continuous action space. Using this framework, we construct a generative scheme, trained using an off-policy actor-critic paradigm, which we call the Generative Actor Critic (GAC). Compared to policy gradient methods, GAC does not require knowledge of the underlying probability distribution, thereby overcoming these limitations. Empirical evaluation shows that our approach is comparable and often surpasses current state-of-the-art baselines in continuous domains.