文件列表:

deep-q-learning/ (0, 2020-10-02)
deep-q-learning/Makefile (110, 2020-10-02)
deep-q-learning/configs/ (0, 2020-10-02)
deep-q-learning/configs/np_linear.py (1054, 2020-10-02)
deep-q-learning/configs/q2_linear.py (1053, 2020-10-02)
deep-q-learning/configs/q3_nature.py (1057, 2020-10-02)
deep-q-learning/configs/q4_train_atari_linear.py (1223, 2020-10-02)
deep-q-learning/configs/q5_train_atari_nature.py (1224, 2020-10-02)
deep-q-learning/configs/q6_bonus_question.py (1061, 2020-10-02)
deep-q-learning/configs/temp.txt (12, 2020-10-02)
deep-q-learning/configs/test.py (1052, 2020-10-02)
deep-q-learning/core/ (0, 2020-10-02)
deep-q-learning/core/deep_q_learning.py (6805, 2020-10-02)
deep-q-learning/core/q_learning.py (10817, 2020-10-02)
deep-q-learning/core/temp.txt (12, 2020-10-02)
deep-q-learning/q1_schedule.py (3724, 2020-10-02)
deep-q-learning/q2_linear.py (8839, 2020-10-02)
deep-q-learning/q3_nature.py (2722, 2020-10-02)
deep-q-learning/q4_train_atari_linear.py (1550, 2020-10-02)
deep-q-learning/q5_train_atari_nature.py (1548, 2020-10-02)
deep-q-learning/requirements.txt (90, 2020-10-02)
deep-q-learning/temp.txt (12, 2020-10-02)
deep-q-learning/utils/ (0, 2020-10-02)
deep-q-learning/utils/general.py (5290, 2020-10-02)
deep-q-learning/utils/preprocess.py (892, 2020-10-02)
deep-q-learning/utils/replay_buffer.py (7722, 2020-10-02)
deep-q-learning/utils/temp.txt (12, 2020-10-02)
deep-q-learning/utils/test_env.py (1823, 2020-10-02)
deep-q-learning/utils/test_env_old.py (1721, 2020-10-02)
deep-q-learning/utils/viewer.py (1672, 2020-10-02)
deep-q-learning/utils/wrappers.py (3175, 2020-10-02)
policy-gradient/ (0, 2020-10-02)
policy-gradient/Makefile (101, 2020-10-02)
policy-gradient/code/ (0, 2020-10-02)
policy-gradient/code/baseline_network.py (3159, 2020-10-02)
policy-gradient/code/config.py (4812, 2020-10-02)
... ...

# stanford-rl [Policy & Value Iteration Docs](https://github.com/reinforcement-learning-explorations/stanford-rl/blob/master/policy-value-iteration/README.md) ### __WORKING ITEMS__ ---

• Move to a completely numpy centric style.
  1. It will be faster & more space efficient
  2. It will be more adaptable to future AI techniques & concepts
  3. It will develop linear algebra related reasoning skill & general comfort

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：