[LeetCode-316] Remove Duplicate Letters
ยท
๐Ÿข One step
LeetCode-316 Remove Duplicate Letters : Given a string s, remove duplicate letters so that every letter appears once and only once. You must make sure your result is the smallest in lexicographical order among all possible results. note :Answer :::python class Solution: def removeDuplicateLetters(self, s: str) -> str: for char in sorted(set(s)): suffix = s[s.index(char):] if set(s)==set(suffix):..
[RL] M1 Mac Mujoco_py ์„ค์น˜ (gcc@9 error)
ยท
๐Ÿ‘พ Deep Learning
https://github.com/deepmind/mujoco/releases Releases · deepmind/mujoco Multi-Joint dynamics with Contact. A general purpose physics simulator. - deepmind/mujoco github.com Mujoco_py pip ์„ค์น˜ ์ „ ์ˆ˜ํ–‰ ์ž‘์—… https://github.com/openai/mujoco-py/issues/662 Support MuJoCo 2.1.1 (including arm64 mac support) · Issue #662 · openai/mujoco-py I hope this can be a tracking issue for supporting MuJoCo 2.1.1, which ..
[leetcode-20] Valid Parenthese
ยท
๐Ÿข One step
LeetCode-20 Valid Parentheses : Given a string s containing just the characters (, ), {, }, [ and ], determine if the input string is valid. note : s consists of parentheses only ()[]{}Answer :::python class Solution: def isValid(self, s: str) -> bool: valid = [] dict_valid = { "}":"{", "]":"[", ")":"(" } for l in s: if l not in dict_valid: valid.append(l) elif not valid or dict_valid[l] != vali..
[RL] A3C (๋น„๋™๊ธฐ Advantage Actor-Critic) ์ •๋ฆฌ
ยท
๐Ÿ‘พ Deep Learning
Policy-Based ๊ธฐ์กด์— Value Based ์ฆ‰ Q-value๋ฅผ ์˜ˆ์ธกํ•˜๋Š” ๋ฐฉ์‹์€ State์™€ action์— ์˜์กดํ•ด ํ•ญ์ƒ trajectories(state-action-reward sequence)๋ฅผ ๊ตฌํ•ด๋‚˜๊ฐ€์•ผํ•˜๋Š” ์ œ์•ฝ์ด ์žˆ์—ˆ๋‹ค. ํ•˜์ง€๋งŒ Policy-Based๋Š” Q-value๋ฟ ์•„๋‹ˆ๋ผ Policy์— ๋Œ€ํ•œ ์ถ”์ •๋„ ๊ฐ™์ดํ•˜๋Š” ๊ฒƒ์ด๋‹ค. ์šฐ๋ฆฌ๊ฐ€ ์›ํ•˜๋Š” ๊ฒƒ์€ Agent๊ฐ€ ์˜ฌ๋ฐ”๋ฅธ ๊ธธ๋กœ ๊ฐ€๋Š” ์ „๋žต์„ ์ฐพ๋Š” ๊ฒƒ์œผ๋กœ Policy-Based๊ฐ€ ์ด๋ฅผ ๋” ์ž˜ ๋ฐ˜์˜ํ•ด์ฃผ์—ˆ๋‹ค. ์žฅ์ ์œผ๋กœ๋Š” - policy๋ฅผ ์ง์ ‘ ํ•™์Šตํ•˜๋ฏ€๋กœ ์•ˆ์ •์„ฑ์ด ๋†’๋‹ค.(ํ™˜๊ฒฝ ๋ณ€ํ™”, ๋…ธ์ด์ฆˆ์— ๋œ ๋ฏผ๊ฐ) - ํ™•๋ฅ ์ ์ธ ์ •์ฑ…(Exploration, Exploitation) ์‚ฌ์ด์˜ ๊ท ํ˜•์„ ์กฐ์ ˆํ•˜๋ฉด์„œ π*(Optimal Policy)๋ฅผ ํ•™์Šต - Continuous spa..
[WARNING:torch.distributed.run] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid
ยท
๐Ÿ Python
https://you.com/search?q=setting+omp_num_threads+environment+variable+for+each+process+to+be+1+in+default%2C+to+avoid+your+system+being+overloaded%2C+please+further+tune+the+variable+for+optimal+performance+in+your+application+as+needed.&tbm=youchat&cfr=chatb&cid=c2_fb5a239a-f7d6-44eb-88d6-662025275ef2 OMP_NUM_THREADS๋Š” OpenMP ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๊ฐ€ ๋ณ‘๋ ฌ ์ฒ˜๋ฆฌ๋ฅผ ์œ„ํ•ด ์‚ฌ์šฉํ•˜๋Š” ์Šค๋ ˆ๋“œ ์ˆ˜๋ฅผ ์„ค์ •ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ํ™˜๊ฒฝ ๋ณ€์ˆ˜์ž…๋‹ˆ๋‹ค. ๊ธฐ๋ณธ์ ์œผ๋กœ 1๋กœ ์„ค์ •ํ•˜๋ฉด ์—ฌ๋Ÿฌ ์Šค๋ ˆ..
[RL] A3C (Asynchronous Advantage Actor-Critic)
ยท
๐Ÿ‘พ Deep Learning
https://github.com/seohyunjun/RL_A3C GitHub - seohyunjun/RL_A3C: A3C (asynchronous advantage actor-critic) A3C (asynchronous advantage actor-critic). Contribute to seohyunjun/RL_A3C development by creating an account on GitHub. github.com
๋‹คํ–ˆ๋‹ค
B's