PACE N OISE FOR E XPLORATION

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 offand 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.

[1]  Shane Legg,et al.  Noisy Networks for Exploration , 2017, ICLR.

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

[3]  Shipra Agrawal,et al.  Near-Optimal Regret Bounds for Thompson Sampling , 2017, J. ACM.

[4]  Alexei A. Efros,et al.  Curiosity-Driven Exploration by Self-Supervised Prediction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

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

[7]  A. P. Hyper-parameters.  Count-Based Exploration with Neural Density Models , 2017 .

[8]  Pieter Abbeel,et al.  Benchmarking Deep Reinforcement Learning for Continuous Control , 2016, ICML.

[9]  Tom Schaul,et al.  Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.

[10]  Tom Schaul,et al.  Prioritized Experience Replay , 2015, ICLR.

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

[12]  Benjamin Van Roy,et al.  Generalization and Exploration via Randomized Value Functions , 2014, ICML.

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

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

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

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

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

[18]  Marc G. Bellemare,et al.  The Arcade Learning Environment: An Evaluation Platform for General Agents , 2012, J. Artif. Intell. Res..

[19]  Tom Schaul,et al.  High dimensions and heavy tails for natural evolution strategies , 2011, GECCO '11.

[20]  Tom Schaul,et al.  A Natural Evolution Strategy for Multi-objective Optimization , 2010, PPSN.

[21]  Tom Schaul,et al.  Exponential natural evolution strategies , 2010, GECCO '10.

[22]  Frank Sehnke,et al.  Parameter-exploring policy gradients , 2010, Neural Networks.

[23]  Tom Schaul,et al.  Efficient natural evolution strategies , 2009, GECCO.

[24]  Tom Schaul,et al.  Stochastic search using the natural gradient , 2009, ICML '09.

[25]  Jürgen Schmidhuber,et al.  State-Dependent Exploration for Policy Gradient Methods , 2008, ECML/PKDD.

[26]  Tom Schaul,et al.  Natural Evolution Strategies , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[27]  Michael Kearns,et al.  Near-Optimal Reinforcement Learning in Polynomial Time , 2002, Machine Learning.

[28]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[29]  Ananth Ranganathan,et al.  The Levenberg-Marquardt Algorithm , 2004 .

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

[31]  Sham M. Kakade,et al.  A Natural Policy Gradient , 2001, NIPS.

[32]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[33]  H. P. Schwefel,et al.  Numerische Optimierung von Computermodellen mittels der Evo-lutionsstrategie , 1977 .

[34]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[35]  G. Uhlenbeck,et al.  On the Theory of the Brownian Motion , 1930 .