Joshua Achiam
Joshua Achiam
PhD Student, UC Berkeley; Research Scientist, OpenAI.
Verified email at berkeley.edu
Title
Cited by
Cited by
Year
On First-Order Meta-Learning Algorithms
A Nichol, J Achiam, J Schulman
arXiv preprint arXiv:1803.02999, 2018
4232018
Constrained Policy Optimization
J Achiam, D Held, A Tamar, P Abbeel
arXiv preprint arXiv:1705.10528, 2017
3062017
Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
J Achiam, S Sastry
arXiv preprint arXiv:1703.01732, 2017
992017
Towards Characterizing Divergence in Deep Q-Learning
J Achiam, E Knight, P Abbeel
arXiv preprint arXiv:1903.08894, 2019
382019
Variational Option Discovery Algorithms
J Achiam, H Edwards, D Amodei, P Abbeel
arXiv preprint arXiv:1807.10299, 2018
382018
Spinning Up in Deep Reinforcement Learning
J Achiam
https://spinningup.openai.com, 0
26*
Benchmarking Safe Exploration in Deep Reinforcement Learning
A Ray, J Achiam, D Amodei
https://cdn.openai.com/safexp-short.pdf, 2019
202019
Responsive safety in reinforcement learning by pid lagrangian methods
A Stooke, J Achiam, P Abbeel
International Conference on Machine Learning, 9133-9143, 2020
62020
Advanced Policy Gradient Methods
J Achiam
Lecture [online] http://rail.eecs.berkeley.edu/deeprlcourse-fa17/f17docs …, 2017
32017
Training Dynamics Models for Accurate Long-Horizon Prediction
E Knight, J Achiam, UC OpenAI
The system can't perform the operation now. Try again later.
Articles 1–10