Questions tagged [policy-gradients]

For questions related to reinforcement learning algorithms often referred to as "policy gradients" (or "policy gradient algorithms"), which attempt to directly optimise a parameterised policy (without first attempting to estimate value functions) using gradients of an objective function with respect to the policy's parameters.

Filter by
Sorted by
Tagged with
11
votes
1answer
5k views

How can policy gradients be applied in the case of multiple continuous actions?

Trusted Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are two cutting edge policy gradients algorithms. When using a single continuous action, normally, you would use some ...
2
votes
2answers
134 views

Advantage computed the wrong way?

Here is the code written by Maxim Lapan. I am reading his book (Deep Reinforcement Learning Hands-on). I have seen a line in his code which is really weird. In the accumulation of the policy gradient $...
2
votes
0answers
68 views

Is this the correct gradient for log of softmax? [duplicate]

I am currently implementing the very basic version (REINFORCE) of the Monte Carlo policy gradient algorithm. I was wondering if this is the correct gradient for the log of softmax. \begin{align} \...
2
votes
1answer
68 views

How do I derive the gradient with respect to the parameters of the softmax policy?

The gradient of the softmax eligibility trace is given by the following: \begin{align} \nabla_{\theta} \log(\pi_{\theta}(a|s)) &= \phi(s,a) - \mathbb E[\phi (s, \cdot)]\\ &= \phi(s,a) - \sum_{...
2
votes
1answer
229 views

What information should be cached in experience replay for actor-critic?

Experience replay is buffer (or a "memory") of transactions $e_t = (s_t, a_t, r_t, s_{t+1})$. The equations for calculating the loss in actor critic are an actor loss (parameterized by $\theta$) $$...