Upload 2 files
Browse files- emo-v36-paper(ENG).txt +52 -2
- emo-v36-paper(JPN).txt +1 -1
emo-v36-paper(ENG).txt
CHANGED
|
@@ -80,7 +80,57 @@ Efficiency improvements for EmoNavi, EmoFact, and EmoLynx:
|
|
| 80 |
|
| 81 |
Supplementary Material (2): Formal Proof of emoDrive Boundedness
|
| 82 |
|
| 83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
In summary, EmoNAVI encapsulates three forms of "intelligence" within a single update loop:
|
| 86 |
|
|
@@ -91,7 +141,7 @@ In summary, EmoNAVI encapsulates three forms of "intelligence" within a single u
|
|
| 91 |
Action Intelligence (emoDrive): Autonomously decides the "step-size" based on the judgment, similar to COCOB or D-adaptation.
|
| 92 |
|
| 93 |
|
| 94 |
-
|
| 95 |
|
| 96 |
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
|
| 97 |
|
|
|
|
| 80 |
|
| 81 |
Supplementary Material (2): Formal Proof of emoDrive Boundedness
|
| 82 |
|
| 83 |
+
1. Objective
|
| 84 |
+
|
| 85 |
+
We prove that emoDrive, which applies a dynamic correction to the learning rate in the EmoNAVI update rule, possesses both upper and lower bounds at any step t. This guarantees that the update magnitude \Delta w_t does not explode and that the convergence conditions are satisfied.
|
| 86 |
+
|
| 87 |
+
2. Lemma: Boundedness of the Emotional Scalar \sigma _t
|
| 88 |
+
|
| 89 |
+
The emotional scalar in EmoNAVI takes the form
|
| 90 |
+
\sigma _t=\tanh (x).
|
| 91 |
+
From the properties of the hyperbolic tangent function, the following holds for any input x\in \mathbb{R}:
|
| 92 |
+
-1<\sigma _t<1.
|
| 93 |
+
Therefore, the absolute value |\sigma _t| always lies within the interval [0,1).
|
| 94 |
+
|
| 95 |
+
3. Theorem: Proof of the Boundedness of emoDrive
|
| 96 |
+
|
| 97 |
+
Based on the implementation code (v3.6.1), the definition of emoDrive is evaluated by dividing it into the following three regions:
|
| 98 |
+
|
| 99 |
+
(A) Normal Zone (No Intervention Zone):
|
| 100 |
+
|\sigma _t|\leq 0.25\quad \mathrm{or}\quad 0.5<|\sigma _t|\leq 0.75
|
| 101 |
+
In this region, according to the implementation, the value is:
|
| 102 |
+
\mathrm{emoDrive}=1.0.
|
| 103 |
+
|
| 104 |
+
(B) Acceleration Zone (emoDrive Active Region):
|
| 105 |
+
0.25<|\sigma _t|<0.5
|
| 106 |
+
In this region, emoDrive is defined as:
|
| 107 |
+
\mathrm{emoDrive}=\mathrm{emoDpt}\times (1.0+0.1\cdot \mathrm{trust}),
|
| 108 |
+
where
|
| 109 |
+
\mathrm{emoDpt}=8.0\times |\mathrm{trust}|,
|
| 110 |
+
and trust is the signed value of (1.0-|\sigma _t|).
|
| 111 |
+
- Evaluation of |\mathrm{trust}|:
|
| 112 |
+
For |\sigma _t|\in (0.25,0.5), we have
|
| 113 |
+
|\mathrm{trust}|\in (0.5,0.75).- Range of emoDpt:
|
| 114 |
+
8.0\times 0.5<\mathrm{emoDpt}<8.0\times 0.75- hence
|
| 115 |
+
4.0<\mathrm{emoDpt}<6.0.- Overall evaluation:
|
| 116 |
+
The factor 1.0+0.1\cdot \mathrm{trust} lies within the range 0.9 to 1.1 regardless of the sign of trust.
|
| 117 |
+
Therefore, the maximum value B_{\mathrm{up}} in the acceleration zone satisfies:
|
| 118 |
+
B_{\mathrm{up}}<6.0\times 1.1=6.6.
|
| 119 |
+
|
| 120 |
+
(C) Emergency Zone (Rapid Braking Zone):
|
| 121 |
+
|\sigma _t|>0.75
|
| 122 |
+
In this region,
|
| 123 |
+
\mathrm{emoDrive}=\mathrm{coeff},
|
| 124 |
+
where
|
| 125 |
+
\mathrm{coeff}=1.0-|\mathrm{scalar}|.
|
| 126 |
+
Since |\sigma _t|\in (0.75,1.0), the minimum value B_{\mathrm{low}} satisfies:
|
| 127 |
+
0<B_{\mathrm{low}}\leq 0.25.
|
| 128 |
+
|
| 129 |
+
4. Conclusion
|
| 130 |
+
From the above evaluations, we have proven that emoDrive satisfies the following boundedness condition in all regions:
|
| 131 |
+
0<(1-|\sigma _{\max }|)\leq \mathrm{emoDrive}\leq 6.6.
|
| 132 |
+
(Even when |\sigma _t| approaches 1, implementation details such as eps ensure that a small positive value is maintained.)
|
| 133 |
+
The existence of this bounded multiplicative coefficient provides the mathematical foundation that allows EmoNAVI to retain the Adam‑type convergence rate O(1/T) while achieving constant‑factor acceleration.
|
| 134 |
|
| 135 |
In summary, EmoNAVI encapsulates three forms of "intelligence" within a single update loop:
|
| 136 |
|
|
|
|
| 141 |
Action Intelligence (emoDrive): Autonomously decides the "step-size" based on the judgment, similar to COCOB or D-adaptation.
|
| 142 |
|
| 143 |
|
| 144 |
+
References
|
| 145 |
|
| 146 |
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
|
| 147 |
|
emo-v36-paper(JPN).txt
CHANGED
|
@@ -128,7 +128,7 @@ emoDrive=1.0
|
|
| 128 |
行動の知能 (emoDrive): 判定に基づき、COCOB や D-adapt のように「歩幅(Step-size)」を自律的に決定する。
|
| 129 |
|
| 130 |
|
| 131 |
-
|
| 132 |
|
| 133 |
Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization.
|
| 134 |
|
|
|
|
| 128 |
行動の知能 (emoDrive): 判定に基づき、COCOB や D-adapt のように「歩幅(Step-size)」を自律的に決定する。
|
| 129 |
|
| 130 |
|
| 131 |
+
参考文献 (References)
|
| 132 |
|
| 133 |
Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization.
|
| 134 |
|