我的随笔

Phasic Policy Gradient

initial_h 2023-04-06 23:43 阅读:115 评论:0 推荐:0 编辑

The Predictron: End-To-End Learning and Planning

initial_h 2023-04-03 10:48 阅读:28 评论:0 推荐:0 编辑

Sample-Based Learning and Search with Permanent and Transient Memories

initial_h 2023-03-30 12:02 阅读:27 评论:0 推荐:0 编辑

Learning model-based planning from scratch

initial_h 2023-03-27 23:24 阅读:32 评论:0 推荐:0 编辑

Discretizing Continuous Action Space for On-Policy Optimization

initial_h 2023-03-23 12:04 阅读:31 评论:0 推荐:0 编辑

Finite-time Analysis of the Multiarmed Bandit Problem

initial_h 2023-03-20 07:45 阅读:110 评论:0 推荐:0 编辑

Disentangling the independently controllable factors of variation by interacting with the world

initial_h 2023-03-18 23:35 阅读:14 评论:0 推荐:0 编辑

COMBINING Q-LEARNING AND SEARCH WITH AMORTIZED VALUE ESTIMATES

initial_h 2023-03-06 01:03 阅读:42 评论:0 推荐:0 编辑

Bandit based Monte-Carlo Planning

initial_h 2023-03-04 00:18 阅读:69 评论:0 推荐:0 编辑

Monte-Carlo tree search as regularized policy optimization

initial_h 2023-02-25 23:04 阅读:58 评论:0 推荐:0 编辑

HIERARCHICAL REINFORCEMENT LEARNING BY DISCOVERING INTRINSIC OPTIONS

initial_h 2022-12-07 08:44 阅读:61 评论:0 推荐:0 编辑

PROCEDURAL GENERALIZATION BY PLANNING WITH SELF-SUPERVISED WORLD MODELS

initial_h 2022-11-25 12:28 阅读:31 评论:0 推荐:0 编辑

Deep Exploration via Bootstrapped DQN

initial_h 2022-06-06 23:46 阅读:271 评论:0 推荐:1 编辑

Policy Distillation

initial_h 2022-06-06 23:44 阅读:96 评论:0 推荐:0 编辑

MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

initial_h 2022-06-02 21:52 阅读:91 评论:0 推荐:0 编辑