Scribd
Upload
26 views

9 Sqoop Notes

The document discusses policy gradient algorithms for reinforcement learning. It covers: 1) How policy gradients directly optimize the reinforcement learning objective by taking gradients of the expected return with respect to the policy parameters. 2) Methods for reducing the high variance in policy gradient estimates, including using baselines and importance sampling. 3) Practical considerations for implementing policy gradients in deep reinforcement learning problems using tools like automatic differentiation.

Uploaded by

pavancreative81
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
26 views

9 Sqoop Notes

The document discusses policy gradient algorithms for reinforcement learning. It covers: 1) How policy gradients directly optimize the reinforcement learning objective by taking gradients of the expected return with respect to the policy parameters. 2) Methods for reducing the high variance in policy gradient estimates, including using baselines and importance sampling. 3) Practical considerations for implementing policy gradients in deep reinforcement learning problems using tools like automatic differentiation.

Uploaded by

pavancreative81
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 35

Policy Gradients

CS 294-112: Deep Reinforcement Learning


Sergey Levine
Class Notes
1. Homework 1 milestone due today (11:59 pm)!
• Don’t be late!
2. Remember to start forming final project groups
Today’s Lecture
1. The policy gradient algorithm
2. What does the policy gradient do?
3. Basic variance reduction: causality
4. Basic variance reduction: baselines
5. Policy gradient examples
• Goals:
• Understand policy gradient reinforcement learning
• Understand practical considerations for policy gradients
The goal of reinforcement learning
we’ll come back to partially observed later
The goal of reinforcement learning

infinite horizon case finite horizon case


Evaluating the objective
Direct policy differentiation
a convenient identity
Direct policy differentiation
Evaluating the policy gradient

fit a model to
estimate return

generate samples
(i.e. run the policy)

improve the policy


Evaluating the policy gradient
Comparison to maximum likelihood

training supervised
data learning
Example: Gaussian policies
What did we just do?

good stuff is made more likely


bad stuff is made less likely
simply formalizes the notion of “trial and error”!
Partial observability
What is wrong with the policy gradient?

high variance

slow convergence
hard to choose learning rate

(image from Peters & Schaal 2008)


Review
• Evaluating the RL objective
• Generate samples
fit a model to
• Evaluating the policy gradient estimate return

• Log-gradient trick generate


samples (i.e.
• Generate samples run the policy)

• Understanding the policy gradient improve the


• Formalization of trial-and-error policy

• Partial observability
• Works just fine
• What is wrong with policy gradient?
Break
Reducing variance

“reward to go”
a convenient identity
Baselines

but… are we allowed to do that??

subtracting a baseline is unbiased in expectation!

average reward is not the best baseline, but it’s pretty good!
Analyzing variance

This is just expected reward, but weighted


by gradient magnitudes!
Review
• The high variance of policy gradient
• Exploiting causality fit a model to
• Future doesn’t affect the past estimate return

• Baselines generate
samples (i.e.
• Unbiased! run the policy)

• Analyzing variance improve the


policy
• Can derive optimal baselines
Policy gradient is on-policy

• Neural networks change only a little bit


with each gradient step
• On-policy learning can be extremely
inefficient!
Off-policy learning & importance sampling
importance sampling
Deriving the policy gradient with IS
a convenient identity
The off-policy policy gradient
A first-order approximation for IS (preview)

We’ll see why this is reasonable


later in the course!
Policy gradient with automatic differentiation
Policy gradient with automatic differentiation
Pseudocode example (with discrete actions):

Maximum likelihood:
# Given:
# actions - (N*T) x Da tensor of actions
# states - (N*T) x Ds tensor of states
# Build the graph:
logits = policy.predictions(states) # This should return (N*T) x Da tensor of action logits
negative_likelihoods = tf.nn.softmax_cross_entropy_with_logits(labels=actions, logits=logits)
loss = tf.reduce_mean(negative_likelihoods)
gradients = loss.gradients(loss, variables)
Policy gradient with automatic differentiation
Pseudocode example (with discrete actions):

Policy gradient:
# Given:
# actions - (N*T) x Da tensor of actions
# states - (N*T) x Ds tensor of states
# q_values – (N*T) x 1 tensor of estimated state-action values
# Build the graph:
logits = policy.predictions(states) # This should return (N*T) x Da tensor of action logits
negative_likelihoods = tf.nn.softmax_cross_entropy_with_logits(labels=actions, logits=logits)
weighted_negative_likelihoods = tf.multiply(negative_likelihoods, q_values)
loss = tf.reduce_mean(weighted_negative_likelihoods)
gradients = loss.gradients(loss, variables)

q_values
Policy gradient in practice
• Remember that the gradient has high variance
• This isn’t the same as supervised learning!
• Gradients will be really noisy!
• Consider using much larger batches
• Tweaking learning rates is very hard
• Adaptive step size rules like ADAM can be OK-ish
• We’ll learn about policy gradient-specific learning rate adjustment methods
later!
Review
• Policy gradient is on-policy
• Can derive off-policy variant
fit a model to
• Use importance sampling estimate return
• Exponential scaling in T
generate
• Can ignore state portion samples (i.e.
(approximation) run the policy)

• Can implement with automatic improve the


differentiation – need to know what policy

to backpropagate
• Practical considerations: batch size,
learning rates, optimizers
Advanced policy gradient topics

• What more is there?


• Next time: introduce value functions and Q-functions
• Later in the class: natural gradient and automatic step size
adjustment
Example: policy gradient with importance sampling

• Incorporate example
demonstrations using
importance sampling
• Neural network policies

Levine, Koltun ‘13


Example: trust region policy optimization
• Natural gradient with
automatic step
adjustment (we’ll
learn about this later)
• Discrete and
continuous actions
• Code available (see
Duan et al. ‘16)

Schulman, Levine, Moritz, Jordan, Abbeel. ‘15


Policy gradients suggested readings
• Classic papers
• Williams (1992). Simple statistical gradient-following algorithms for connectionist
reinforcement learning: introduces REINFORCE algorithm
• Baxter & Bartlett (2001). Infinite-horizon policy-gradient estimation: temporally
decomposed policy gradient (not the first paper on this! see actor-critic section later)
• Peters & Schaal (2008). Reinforcement learning of motor skills with policy gradients:
very accessible overview of optimal baselines and natural gradient
• Deep reinforcement learning policy gradient papers
• Levine & Koltun (2013). Guided policy search: deep RL with importance sampled policy
gradient (unrelated to later discussion of guided policy search)
• Schulman, L., Moritz, Jordan, Abbeel (2015). Trust region policy optimization: deep RL
with natural policy gradient and adaptive step size
• Schulman, Wolski, Dhariwal, Radford, Klimov (2017). Proximal policy optimization
algorithms: deep RL with importance sampled policy gradient

You might also like