Learning and Querying Fast Generative Models for Reinforcement Learning

A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accuracy makes their application in RL feasible: We demonstrate that agents which query these models for decision making outperform strong model-free baselines on the game MSPACMAN, demonstrating the potential of using learned environment models for planning.

[1]  Ole Winther,et al.  Sequential Neural Models with Stochastic Layers , 2016, NIPS.

[2]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[3]  Uri Shalit,et al.  Deep Kalman Filters , 2015, ArXiv.

[4]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[5]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[6]  Daan Wierstra,et al.  Recurrent Environment Simulators , 2017, ICLR.

[7]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[8]  Richard S. Sutton,et al.  Dyna, an integrated architecture for learning, planning, and reacting , 1990, SGAR.

[9]  J. Betts Survey of Numerical Methods for Trajectory Optimization , 1998 .

[10]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[11]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[12]  Razvan Pascanu,et al.  Imagination-Augmented Agents for Deep Reinforcement Learning , 2017, NIPS.

[13]  Sergey Levine,et al.  Deep visual foresight for planning robot motion , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Thomas B. Schön,et al.  From Pixels to Torques: Policy Learning with Deep Dynamical Models , 2015, ICML 2015.

[15]  Honglak Lee,et al.  Action-Conditional Video Prediction using Deep Networks in Atari Games , 2015, NIPS.

[16]  Richard E. Turner,et al.  Neural Adaptive Sequential Monte Carlo , 2015, NIPS.

[17]  Pieter Abbeel,et al.  Value Iteration Networks , 2016, NIPS.

[18]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[19]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[20]  Erik Talvitie,et al.  Agnostic System Identification for Monte Carlo Planning , 2015, AAAI.

[21]  Il Memming Park,et al.  BLACK BOX VARIATIONAL INFERENCE FOR STATE SPACE MODELS , 2015, 1511.07367.

[22]  Tom Schaul,et al.  Rainbow: Combining Improvements in Deep Reinforcement Learning , 2017, AAAI.

[23]  Sergey Levine,et al.  Stochastic Variational Video Prediction , 2017, ICLR.

[24]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[25]  Jitendra Malik,et al.  Learning to Poke by Poking: Experiential Learning of Intuitive Physics , 2016, NIPS.

[26]  Yann LeCun,et al.  Model-Based Planning in Discrete Action Spaces , 2017, ArXiv.

[27]  Tom Schaul,et al.  Reinforcement Learning with Unsupervised Auxiliary Tasks , 2016, ICLR.

[28]  Yann LeCun,et al.  Model-Based Planning with Discrete and Continuous Actions , 2017 .

[29]  Martin A. Riedmiller,et al.  Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images , 2015, NIPS.

[30]  Tom Schaul,et al.  The Predictron: End-To-End Learning and Planning , 2016, ICML.

[31]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[32]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[33]  Marc G. Bellemare,et al.  The Arcade Learning Environment: An Evaluation Platform for General Agents (Extended Abstract) , 2012, IJCAI.

[34]  Satinder Singh,et al.  Value Prediction Network , 2017, NIPS.

[35]  Romain Laroche,et al.  Hybrid Reward Architecture for Reinforcement Learning , 2017, NIPS.