+FUTPO/BOPͰಈ͘ਂ૚ڧԽֶशΛ࢖ͬͨ ϥδίϯ޲͚ࣗಈӡసιϑτ΢ΣΞͷ঺հ *P5"-(:"/प೥*P5ࡇ !NBTBUP@LB

͋͞ʂ"*3$$BSΛ࢝ΊΑ͏ ࢢൢϥδίϯ4#$ "*ͱΧϝϥͷΈ -&7&-૬౰ͷ૸ߦ ੈքதͰϨʔε͕։࠵͞Ε͍ͯΔ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

"*3$$BS૸ߦͷ࢓૊Έ 4FMG%SJWJOH $JSDVJU ……….. ڭࣔσʔλͷऩू "*ͷֶश ਪ࿦૸ߦ "*Λ࢖͍ೝ஌͔Β൑அ·Ͱ&OEUP&OEͰ૸ߦ͢Δ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

"*3$$BSϨʔεͰউͭͨΊʹʂ ϋʔυ΢ΣΞ "*$7੍ޚ ύΠϩοτదੑ ڭࣔσʔλ͕উഊΛେ͖͘࡞༻͢Δ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

͓खຊͳ͠ʹ૸ΓํΛֶͿਂ૚ڧԽֶश ࢼߦͱใु͔Βྑ͍૸Γͷಛ௃ΛֶͿ 4FMG%SJWJOH $JSDVJU ΞΫγϣϯ Environment AI͕σʔλΛ ूΊΔɻ ※ใुͷ૯࿨͕࠷େͱͳΔΑ͏ͳಈ͖ํΛ୳ࡧ͍ͯ͠Δɻ ใु,ঢ়ଶ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN Jetson NanoͰ10෼ʙ20෼Ͱ૸ߦํ๏Λ֫ಘ

࣮૷ͨ͠ιϑτ΢ΣΞͷಛ௃ JETSON NANO SAC VAE Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290, 2018. ΤοδͰਂ૚ڧԽֶशΛ͢ΔͨΊͷ޻෉ Antonin Raffin, Learning to Drive Smoothly in Minutes Reinforcement Learning on a Small Racing Car , 2019. ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

ιϑτͷެ։ͱ൓ڹ (JUIVCͷ3&"%.&͸ӳޠ (PPHMF຋༁ Ͱެ։ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN /7*%*"͞Μͷ+FUTPO$PNNVOJUZ1SPKFDUT IUUQTEFWFMPQFSOWJEJBDPNFNCFEEFEDPNNVOJUZKFUTPOQSPKFDUTSFJOGPSDFNFOU@KFUCPU

໨ࢦͤόʔνϟϧϨʔε ੈքதͷϢʔβ͕ࢀՃͯ͠ΦϯϥΠϯͰରઓ γϛϡϨʔλΛ࢖ͬͨϨʔε ΦϯϥΠϯͰϦΞϧλΠϜରઓ ੈքνϟϯϐΦϯ͸೔ຊਓ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

·ͱΊ "*3$$BSΛ࢝ΊͯΈ·ͤΜ͔ʁ "*Ͱܭଌ੍ޚΛֶͿ"*3$$BS ΤοδσόΠεͰਂ૚ڧԽֶश ੈքͷίϛϡχςΟͱܨ͕Ζ͏ ৄ͘͠͸IUUQNBTBUPLBIBUFOBCMPHDPN

No content