Discrete-action algorithms have been central to numerous recent successes of deep reinforcement l... more 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-theart continuous control algorithm, Deep Deterministic Policy Gradient (DDPG).
neural information processing systems, Dec 4, 2017
In reinforcement learning, it is common to let an agent interact for a fixed amount of time with ... more In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state-aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent's input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning. We argue that this insight should be incorporated by bootstrapping from the value of the state at the end of each partial episode. For both cases, we illustrate empirically the significance of our considerations in improving the performance and stability of existing reinforcement learning algorithms, showing state-of-the-art results on several control tasks.
Muscle-actuated control is a research topic of interest spanning different fields, in particular ... more Muscle-actuated control is a research topic of interest spanning different fields, in particular biomechanics, robotics and graphics. This type of control is particularly challenging because models are often overactuated, and dynamics are delayed and non-linear. It is however a very well tested and tuned actuation model that has undergone millions of years of evolution and that involves interesting properties exploiting passive forces of muscle-tendon units and efficient energy storage and release. To facilitate research on muscle-actuated simulation, we release a 3D musculoskeletal simulation of an ostrich based on the MuJoCo simulator. Ostriches are one of the fastest bipeds on earth and are therefore an excellent model for studying muscle-actuated bipedal locomotion. The model is based on CT scans and dissections used to gather actual muscle data such as insertion sites, lengths and pennation angles. Along with this model, we also provide a set of reinforcement learning tasks, in...
We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks... more We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks such that their core functions all exhibit consistent call signatures, syntax and input-output behaviour. Ivy allows high-level framework-agnostic functions to be implemented through the use of framework templates. The framework templates act as placeholders for the specific framework at development time, which are then determined at runtime. The portability of Ivy functions enables their use in projects of any supported framework. Ivy currently supports TensorFlow, PyTorch, MXNet, Jax and NumPy. Alongside Ivy, we release four pure-Ivy libraries for mechanics, 3D vision, robotics, and differentiable environments. Through our evaluations, we show that Ivy can significantly reduce lines of code with a runtime overhead of less than 1% in most cases. We welcome developers to join the Ivy community by writing their own functions, layers and libraries in Ivy, maximizing their audience and hel...
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art c... more Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace single random action choices by random goals selection followed by several steps in their direction. This approach is compatible with any curiosity-based exploration and off-policy reinforcement learning agents and generates longer and safer trajectories than individual random actions. To illustrate this, we present a task-independent agent that learns to reach coordinates in screen frames and demonstrate its ability to explore with the game Super Mario Bros. improving significantly the score of a baseline DQN agent.
In reinforcement learning, it is common to let an agent interact for a fixed amount of time with ... more In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state-aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent's input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning...
International Conference on Machine Learning, 2020
Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in con... more Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in continuous control. We study the problem of learning reusable humanoid skills by imitating motion capture data and joint training with complementary tasks. We show that it is possible to learn reusable skills through reinforcement learning on 50 times more motion capture data than prior work. We systematically compare a variety of different network architectures across different data regimes both in terms of imitation performance as well as transfer to challenging locomotion tasks. Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.
Discrete-action algorithms have been central to numerous recent successes of deep reinforcement l... more 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 cont...
Goal-oriented learning has become a core concept in reinforcement learning (RL), extending the re... more Goal-oriented learning has become a core concept in reinforcement learning (RL), extending the reward signal as a sole way to define tasks. However, as parameterizing value functions with goals increases the learning complexity, efficiently reusing past experience to update estimates towards several goals at once becomes desirable but usually requires independent updates per goal. Considering that a significant number of RL environments can support spatial coordinates as goals, such as on-screen location of the character in ATARI or SNES games, we propose a novel goal-oriented agent called Q-map that utilizes an autoencoder-like neural network to predict the minimum number of steps towards each coordinate in a single forward pass. This architecture is similar to Horde with parameter sharing and allows the agent to discover correlations between visual patterns and navigation. For example learning how to use a ladder in a game could be transferred to other ladders later. We show how t...
We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks... more We introduce Ivy, a templated Deep Learning (DL) framework which abstracts existing DL frameworks such that their core functions all exhibit consistent call signatures, syntax and input-output behaviour. Ivy allows high-level framework-agnostic functions to be implemented through the use of framework templates. The framework templates act as placeholders for the specific framework at development time, which are then determined at runtime. The portability of Ivy functions enables their use in projects of any supported framework. Ivy currently supports TensorFlow, PyTorch, MXNet, Jax and NumPy. Alongside Ivy, we release four pure-Ivy libraries for mechanics, 3D vision, robotics, and differentiable environments. Through our evaluations, we show that Ivy can significantly reduce lines of code with a runtime overhead of less than 1% in most cases. We welcome developers to join the Ivy community by writing their own functions, layers and libraries in Ivy, maximizing their audience and hel...
Goal-oriented learning has become a core concept in reinforcement learning (RL), extending the re... more Goal-oriented learning has become a core concept in reinforcement learning (RL), extending the reward signal as a sole way to define tasks. However, as parameterizing value functions with goals increases the learning complexity, efficiently reusing past experience to update estimates towards several goals at once becomes desirable but usually requires independent updates per goal. Considering that a significant number of RL environments can support spatial coordinates as goals, such as on-screen location of the character in ATARI or SNES games, we propose a novel goal-oriented agent called Q-map that utilizes an autoencoder-like neural network to predict the minimum number of steps towards each coordinate in a single forward pass. This architecture is similar to Horde with parameter sharing and allows the agent to discover correlations between visual patterns and navigation. For example learning how to use a ladder in a game could be transferred to other ladders later. We show how t...
Discrete-action algorithms have been central to numerous recent successes of deep reinforcement l... more 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 cont...
In reinforcement learning, it is common to let an agent interact for a fixed amount of time with ... more In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state-aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent's input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning...
Deep reinforcement learning has been one of the fastest growing fields of machine learning over t... more Deep reinforcement learning has been one of the fastest growing fields of machine learning over the past years and numerous libraries have been open sourced to support research. However, most codebases have a steep learning curve or limited flexibility that do not satisfy a need for fast prototyping in fundamental research. This paper introduces Tonic, a Python library allowing researchers to quickly implement new ideas and measure their importance by providing: 1) a collection of configurable modules such as exploration strategies, replays, neural networks, and updaters 2) a collection of baseline agents: A2C, TRPO, PPO, MPO, DDPG, D4PG, TD3 and SAC built with these modules 3) support for the two most popular deep learning frameworks: TensorFlow 2 and PyTorch 4) support for the three most popular sets of continuous-control environments: OpenAI Gym, DeepMind Control Suite and PyBullet 5) a large-scale benchmark of the baseline agents on 70 continuous-control tasks 6) scripts to expe...
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art c... more Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace single random action choices by random goals selection followed by several steps in their direction. This approach is compatible with any curiosity-based exploration and off-policy reinforcement learning agents and generates longer and safer trajectories than individual random actions. To illustrate this, we present a task-independent agent that learns to reach coordinates in screen frames and demonstrate its ability to explore with the game Super Mario Bros. improving significantly the score of a baseline DQN agent.
Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in con... more Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in continuous control. We study the problem of learning reusable humanoid skills by imitating motion capture data and joint training with complementary tasks. We show that it is possible to learn reusable skills through reinforcement learning on 50 times more motion capture data than prior work. We systematically compare a variety of different network architectures across different data regimes both in terms of imitation performance as well as transfer to challenging locomotion tasks. Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.
Proceedings of the AAAI Conference on Artificial Intelligence
Being able to reach any desired location in the environment can be a valuable asset for an agent.... more Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallel limited the approach to small tabular cases so far. To tackle this problem we propose to use convolutional network architectures to generate Q-values and updates for a large number of goals at once. We demonstrate the accuracy and generalization qualities of the proposed method on randomly generated mazes and Sokoban puzzles. In the case of on-screen goal coordinates the resulting mapping from frames to distance-maps directly informs the agent about which places are reachable and in how many steps. As an example of application we show that replacing the random actions in ε-greedy exploration by several actions towards feasible...
Uploads
Papers by Fabio Pardo