Curiosity-Driven Exploration by Self-Supervised Prediction

In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, critically, ignores the aspects of the environment that cannot affect the agent. The proposed approach is evaluated in two environments: VizDoom and Super Mario Bros. Three broad settings are investigated: 1) sparse extrinsic reward; 2) exploration with no extrinsic reward; and 3) generalization to unseen scenarios (e.g. new levels of the same game).

[1]  Stewart W. Wilson,et al.  A Possibility for Implementing Curiosity and Boredom in Model-Building Neural Controllers , 1991 .

[2]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..


[4]  Michael I. Jordan,et al.  An internal model for sensorimotor integration. , 1995, Science.

[5]  Michael Kearns,et al.  Efficient Reinforcement Learning in Factored MDPs , 1999, IJCAI.

[6]  Ryan,et al.  Intrinsic and Extrinsic Motivations: Classic Definitions and New Directions. , 2000, Contemporary educational psychology.

[7]  Ronen I. Brafman,et al.  R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning , 2001, J. Mach. Learn. Res..

[8]  Nuttapong Chentanez,et al.  Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[9]  Chrystopher L. Nehaniv,et al.  Empowerment: a universal agent-centric measure of control , 2005, 2005 IEEE Congress on Evolutionary Computation.

[10]  Jesse Hoey,et al.  An analytic solution to discrete Bayesian reinforcement learning , 2006, ICML.

[11]  Pierre-Yves Oudeyer,et al.  Intrinsic Motivation Systems for Autonomous Mental Development , 2007, IEEE Transactions on Evolutionary Computation.

[12]  Pierre-Yves Oudeyer,et al.  What is Intrinsic Motivation? A Typology of Computational Approaches , 2007, Frontiers Neurorobotics.

[13]  Jürgen Schmidhuber,et al.  Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010) , 2010, IEEE Transactions on Autonomous Mental Development.

[14]  Yi Sun,et al.  Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments , 2011, AGI.

[15]  Doina Precup,et al.  An information-theoretic approach to curiosity-driven reinforcement learning , 2012, Theory in Biosciences.

[16]  P. Silvia Curiosity and Motivation , 2012 .

[17]  Pierre-Yves Oudeyer,et al.  Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress , 2012, NIPS.

[18]  Friedrich T. Sommer,et al.  Learning and exploration in action-perception loops , 2013, Front. Neural Circuits.

[19]  Sergey Levine,et al.  Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models , 2015, ArXiv.

[20]  Andrew Schartmann Super Mario Bros. , 2015 .

[21]  Jonathan Tompson,et al.  Unsupervised Feature Learning from Temporal Data , 2015, ICLR.

[22]  Nitish Srivastava Unsupervised Learning of Visual Representations using Videos , 2015 .

[23]  Shakir Mohamed,et al.  Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning , 2015, NIPS.

[24]  Kristen Grauman,et al.  Learning Image Representations Tied to Ego-Motion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Jitendra Malik,et al.  Learning to See by Moving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

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

[28]  Alexei A. Efros,et al.  Unsupervised Visual Representation Learning by Context Prediction , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[29]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[30]  Filip De Turck,et al.  VIME: Variational Information Maximizing Exploration , 2016, NIPS.

[31]  Benjamin Van Roy,et al.  Deep Exploration via Bootstrapped DQN , 2016, NIPS.

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

[33]  Tom Schaul,et al.  Unifying Count-Based Exploration and Intrinsic Motivation , 2016, NIPS.

[34]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[36]  Wojciech Jaskowski,et al.  ViZDoom: A Doom-based AI research platform for visual reinforcement learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[37]  J. Schulman,et al.  Variational Information Maximizing Exploration , 2016 .

[38]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[39]  Wojciech Zaremba,et al.  OpenAI Gym , 2016, ArXiv.

[40]  Filip De Turck,et al.  #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning , 2016, NIPS.

[41]  Vladlen Koltun,et al.  Learning to Act by Predicting the Future , 2016, ICLR.

[42]  Justin Fu,et al.  EX2: Exploration with Exemplar Models for Deep Reinforcement Learning , 2017, NIPS.

[43]  Daan Wierstra,et al.  Variational Intrinsic Control , 2016, ICLR.

[44]  Trevor Darrell,et al.  Loss is its own Reward: Self-Supervision for Reinforcement Learning , 2016, ICLR.

[45]  Razvan Pascanu,et al.  Learning to Navigate in Complex Environments , 2016, ICLR.

[46]  Tom Schaul,et al.  Reinforcement Learning with Unsupervised Auxiliary Tasks , 2017, ICLR.

[47]  Ilya Kostrikov,et al.  Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play , 2017, ICLR.