Skip to main content

Questions tagged [trust-region-policy-optimization]

For questions about the Trust Region Policy Optimization (TRPO) algorithm, which was introduced in the paper "Trust Region Policy Optimization" (2015) by J. Schulman et al.

6 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4 votes
1 answer
251 views

In lemma 1 of the TRPO paper, why isn't the expectation over $s'∼P(s'|s,a)$?

In the Trust Region Policy Optimization paper, in Lemma 1 of Appendix A, I didn't quite understand the transition from (21) from (20). In going from (20) to (21), $A^\pi(s_t, a_t)$ is substituted with ...
A Das's user avatar
  • 141
2 votes
0 answers
146 views

How does the TRPO surrogate loss account for the error in the policy?

In the Trust Region Policy Optimization (TRPO) paper, on page 10, it is stated An informal overview is as follows. Our proof relies on the notion of coupling, where we jointly define the ...
olliejday's user avatar
1 vote
0 answers
573 views

Why does PPO lead to a worse performance than TRPO in the same task?

I am training an agent with an Actor-Critic network and update it with TRPO so far. Now, I tried out PPO and the results are drastically different and bad. I only changed from TRPO to PPO, the rest of ...
thsolyt's user avatar
  • 31
0 votes
0 answers
36 views

why PPO performs better than TRPO?

what is the logistic behind why PPO performs better than TRPO(at least in the PPO's paper results)? When I read both papers, it seems like PPO is just simpler version of TRPO, that it does not run ...
user3315463's user avatar
0 votes
0 answers
79 views

CS 285 Prof Sergey Levine Lecture, Bounding Derivation for Reinforcement Learning (TRPO)

How can we derive the final result? I can understand the first line, but don't know how the absolute term in the summation is replaced with $2\epsilon t$. https://www.youtube.com/watch?v=LtAt5M_a0dI&...
shashack's user avatar
  • 101
0 votes
1 answer
108 views

Can TRPO use replay buffers?

I understand that TRPO is a on-policy RL method and that it optimizes an expectation of the advantage or accumulated returns function over actions taken according to policy $\pi$. Is it possible to ...
Wj210's user avatar
  • 1