OpenAI - Welcome to Spinning Up in Deep RL! — Spinning Up …
Resources Spinning Up as a Deep RL Researcher The Right Background Learn by Doing Developing a Research Project Doing Rigorous Research in RL Closing Thoughts PS: Other …
Part 1: Key Concepts in RL — Spinning Up documentation - OpenAI
Reinforcement learning methods are ways that the agent can learn behaviors to achieve its goal. To talk more specifically what RL does, we need to introduce additional terminology.
Part 2: Kinds of RL Algorithms — Spinning Up documentation
The MBMF work explores MPC with learned environment models on some standard benchmark tasks for deep RL. Expert Iteration. A straightforward follow-on to pure planning involves using …
Introduction — Spinning Up documentation - OpenAI
This is an educational resource produced by OpenAI that makes it easier to learn about deep reinforcement learning (deep RL). For the unfamiliar: reinforcement learning (RL) is a machine …
Key Papers in Deep RL — Spinning Up documentation - OpenAI
Reinforcement Learning of Motor Skills with Policy Gradients, Peters and Schaal, 2008. Contributions: Thorough review of policy gradient methods at the time, many of which are still …
Soft Actor-Critic — Spinning Up documentation - OpenAI
To explain Soft Actor Critic, we first have to introduce the entropy-regularized reinforcement learning setting. In entropy-regularized RL, there are slightly-different equations for value …
Spinning Up as a Deep RL Researcher — Spinning Up …
There are a wide range of topics you might find interesting: sample efficiency, exploration, transfer learning, hierarchy, memory, model-based RL, meta learning, and multi-agent, to name a few.
Vanilla Policy Gradient — Spinning Up documentation - OpenAI
Policy Gradient Methods for Reinforcement Learning with Function Approximation, Sutton et al. 2000 Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation …
Deep Deterministic Policy Gradient — Spinning Up documentation …
Q-learning algorithms for function approximators, such as DQN (and all its variants) and DDPG, are largely based on minimizing this MSBE loss function. There are two main tricks employed …
Part 3: Intro to Policy Optimization — Spinning Up documentation …
The simplest method for learning , used in most implementations of policy optimization algorithms (including VPG, TRPO, PPO, and A2C), is to minimize a mean-squared-error objective: