https://github.com/adeelh/rl_high_confidence_policy_improvement
High Confidence Policy Improvement for RL (class project for Reinforcement Learning, Fall 2019)
https://github.com/adeelh/rl_high_confidence_policy_improvement
machine-learning optimization reinforcement-learning
Last synced: about 1 month ago
JSON representation
High Confidence Policy Improvement for RL (class project for Reinforcement Learning, Fall 2019)
- Host: GitHub
- URL: https://github.com/adeelh/rl_high_confidence_policy_improvement
- Owner: AdeelH
- Created: 2019-12-08T00:08:02.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2020-10-31T10:54:48.000Z (over 5 years ago)
- Last Synced: 2025-01-30T14:34:41.464Z (over 1 year ago)
- Topics: machine-learning, optimization, reinforcement-learning
- Language: Python
- Homepage:
- Size: 6.98 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# High Confidence Policy Improvement for RL
Given only the data from previous executions of a policy, but not the policy itself, generate a new policy that is probabilistically guaranteed to be better than the old policy.
For details: https://people.cs.umass.edu/~pthomas/papers/Thomas2015b.pdf