First draft of intro paragraph on DDPG and DQNs #15
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
MadcowD
requested changes
Sep 22, 2016
Member
MadcowD
left a comment
MadcowD
left a comment
There was a problem hiding this comment.
Looks good! Just want some more detail.
|
|
||
| \section{Introduction} | ||
| \todo[inline]{Introduction to DDPG and recent advances in deep RL. } | ||
| [INSERT OPENING SENTENCE HERE] The current state-of-the-art in deep reinforcement learning is the Deep Deterministic Policy Gradient (DDPG) algorithm [\cite{lillicrap2015ddpg}] which expanded the deterministic policy gradient algorithm [\cite{silver2014dpg}] to continuous, high dimensional action spaces, with much success. The basic idea of DDPG is to use an actor-critic algorithm based on the DPG algorithm, where the critic $Q(s, a)$ is learned as in deep Q network learning [\cite{mnih2013dqn}], which is a model-free learning regime, and the actor $\mu(s)$ is updated based on sampling the policy gradient from [\cite{silver2014dpg}]. This algorithm had success comparable to planning based solvers on many physical control problems. |
Member
There was a problem hiding this comment.
This looks good, but I would then add a possibly second paragraph describing the downsides of this algorithm. *We need to motivate the rest of the paper! * Could be about: 1. Divergence, 2. Hyper parameter instability ( some $\gamma$s work and others do not, paradigmatically the method requires a lot of tuning, obviously you need to cite evidence for this argument). 3. The replay buffer is hacky, try and deconstruct the reasons for why it's use is essential for the DDPG algorithm
Member
|
@JamesMBartlett Any updates on this? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.