Skip to content

Commit

Permalink
small changes indices
Browse files Browse the repository at this point in the history
  • Loading branch information
@Reytuag
Reytuag committed Oct 24, 2023
1 parent e40249a commit a2736a6
Show file tree
Hide file tree
Showing 3 changed files with 105 additions and 105 deletions.
70 changes: 35 additions & 35 deletions _site/article.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -347,7 +347,7 @@ <h2 id='Videos'>Videos</h2>

</div>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video SX: Agents obtained by each method<br>
Video S5: Agents obtained by each method<br>
<span style="font-size: 14px;color:#A0A0A0;">
100 Patterns passing our agency tests obtained by random search,IMGEP, handmade search (from Lenia original papers). A lot of IMGEP obtained agents are moving agents with high speed.
</span>
Expand Down Expand Up @@ -421,7 +421,7 @@ <h3 id='Videos'>Generalization</h3>

</div>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video SX: Moving obstacle test on agents obtained by each method<br>
Video S6: Moving obstacle test on agents obtained by each method<br>
<span style="font-size: 14px;color:#A0A0A0;">
100 Agents obtained by random search,IMGEP, handmade search (from Lenia original papers). We observe that the proportion of agents with robustness to moving obstacles is much higher in the agents obtained by IMGEP than the ones obtained
by random search and handmade search.
Expand All @@ -441,7 +441,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed9_142/seed9_crea00142_obstacle_number_var_30.00.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.1<br>
Video S7.1<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle number : 30
</span>
Expand All @@ -453,7 +453,7 @@ <h4> Quantitative</h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.2<br>
Video S7.2<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle radius 7
</span>
Expand All @@ -466,7 +466,7 @@ <h4> Quantitative</h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.3<br>
Video S7.3<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle speed 3
</span>
Expand All @@ -480,7 +480,7 @@ <h4> Quantitative</h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.4<br>
Video S7.4<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update mask rate 0.2
</span>
Expand All @@ -494,7 +494,7 @@ <h4> Quantitative</h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.5<br>
Video S7.5<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update noise rate 0.8
</span>
Expand All @@ -507,7 +507,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed9_142/seed9_crea00142_update_noise_std_var_0.60.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.6<br>
Video S7.6<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update noise std 0.6
</span>
Expand All @@ -520,7 +520,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed9_142/seed9_crea00142_init_noise_rate_var_1.00.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.7<br>
Video S7.7<br>
<span style="font-size: 10px;color:#A0A0A0;">
Init noise rate 1
</span>
Expand All @@ -533,7 +533,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed9_142/seed9_crea00142_init_noise_std_var_4.50.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.8<br>
Video S7.8<br>
<span style="font-size: 10px;color:#A0A0A0;">
Init noise std 4.5
</span>
Expand All @@ -546,7 +546,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed9_142/seed9_crea00142_scaling_var_2.15.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.9<br>
Video S7.9<br>
<span style="font-size: 10px;color:#A0A0A0;">
Rescaling 2.15
</span>
Expand All @@ -571,7 +571,7 @@ <h4> Quantitative</h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.11<br>
Video S7.11<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle number : 30
</span>
Expand All @@ -582,7 +582,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_obstacle_radius_var_7.00.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.12<br>
Video S7.12<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle Radius 7.
</span>
Expand All @@ -594,7 +594,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_obstacle_speed_var_3.00.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.13<br>
Video S7.13<br>
<span style="font-size: 10px;color:#A0A0A0;">
Obstacle speed 3
</span>
Expand All @@ -607,7 +607,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_update_mask_rate_var_0.20.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.14<br>
Video S7.14<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update mask rate 0.2
</span>
Expand All @@ -620,7 +620,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_update_noise_rate_var_0.80.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.15<br>
Video S7.15<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update noise rate 0.8
</span>
Expand All @@ -633,7 +633,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_update_noise_std_var_0.60.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.16<br>
Video S7.16<br>
<span style="font-size: 10px;color:#A0A0A0;">
Update noise std 0.6
</span>
Expand All @@ -647,7 +647,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_init_noise_rate_var_1.00.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.17<br>
Video S7.17<br>
<span style="font-size: 10px;color:#A0A0A0;">
Init noise rate 1.
</span>
Expand All @@ -660,7 +660,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_init_noise_std_var_4.50.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.18<br>
Video S7.18<br>
<span style="font-size: 10px;color:#A0A0A0;">
Init noise std 4.5
</span>
Expand All @@ -673,7 +673,7 @@ <h4> Quantitative</h4>
<source src="public/generalization_seed5_120/seed5_crea00120_scaling_var_2.15.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S5.19<br>
Video S7.19<br>
<span style="font-size: 10px;color:#A0A0A0;">
Rescaling 2.15
</span>
Expand All @@ -685,7 +685,7 @@ <h4> Quantitative</h4>

</div>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video S5 : Illustration of the quantitative tests performed<br>
Video S7 : Illustration of the quantitative tests performed<br>
<span style="font-size: 14px;color:#A0A0A0;">
Videos of quantitative tests for 2 moving agents obtained by IMGEP. We display only a subset of the value tested for every quantitative test.
</span>
Expand All @@ -711,7 +711,7 @@ <h4> Qualitative </h4>
<source src="public/custom_obstacles.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S6: Out of distribution obstacles<br>
Video S8: Out of distribution obstacles<br>
<span style="font-size: 10px;color:#A0A0A0;">
Test of a moving agent obtained by IMGEP on obstacles that were not seen during training.
</span>
Expand All @@ -724,7 +724,7 @@ <h4> Qualitative </h4>
<source src="public/solveMaze.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S7: Out of distribution obstacles, maze.<br>
Video S9: Out of distribution obstacles, maze.<br>
<span style="font-size: 10px;color:#A0A0A0;">
Test of a moving agent to maze like obstacles.
</span>
Expand All @@ -736,7 +736,7 @@ <h4> Qualitative </h4>
<source src="public/harderEnv.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S8: Bullet like environment<br>
Video S10: Bullet like environment<br>
<span style="font-size: 10px;color:#A0A0A0;">
Test of a moving agent to bullet like environment: fast small moving obstacles.
</span>
Expand All @@ -756,7 +756,7 @@ <h4> Qualitative </h4>
<source src="public/demo.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S9: Individuality preservation<br>
Video S11: Individuality preservation<br>
<span style="font-size: 10px;color:#A0A0A0;">
Moving agents colliding while keeping their individuality, they don't merge or collapse from the collision.
</span>
Expand All @@ -771,7 +771,7 @@ <h4> Qualitative </h4>
</video>

<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S10: Reproduction<br>
Video S12: Reproduction<br>
<span style="font-size: 10px;color:#A0A0A0;">
For some moving agents, under specific conditions, the collision of 2 agents can lead to the birth of a 3rd agent.
</span>
Expand All @@ -783,7 +783,7 @@ <h4> Qualitative </h4>
<source src="public/stick.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S11: Attraction<br>
Video S13: Attraction<br>
<span style="font-size: 10px;color:#A0A0A0;">
Moving agents attracting each other while still maintaining their own individuality.
</span>
Expand Down Expand Up @@ -812,7 +812,7 @@ <h4> Qualitative </h4>
<source src="public/asynchro.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S12: Asynchronous update<br>
Video S14: Asynchronous update<br>
<span style="font-size: 10px;color:#A0A0A0;">
Testing a moving agent with asynchronous updates. Each cell is updated with a certain probability at each step leading to cells being asynchronously updated.
</span>
Expand All @@ -824,7 +824,7 @@ <h4> Qualitative </h4>
<source src="public/smallerDie.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S13: Scaling the agents down<br>
Video S15: Scaling the agents down<br>
<span style="font-size: 10px;color:#A0A0A0;">
The moving agents size is reduced. The scaled down agents still seem to behave similarly (same shape and have sensorimotor capabilities) to the normal size one while being composed of less cells.
</span>
Expand All @@ -837,7 +837,7 @@ <h4> Qualitative </h4>
<source src="public/damageHand.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S14: Morphological computation<br>
Video S16: Morphological computation<br>
<span style="font-size: 10px;color:#A0A0A0;">
We pause the simulation and remove some cells of a moving agent. As a response to this alteration of the structure,
the moving agent changes direction, reconstructs itself and moves away.
Expand Down Expand Up @@ -874,7 +874,7 @@ <h4> Qualitative </h4>
<source src="public/attractLive.mp4" type="video/mp4">
</video>
<p style="font-size: 12px;color:#000000;text-align:center;" >
Video S15: External control.<br>
Video S17: External control.<br>
<span style="font-size: 10px;color:#A0A0A0;">
We introduce an attractive element in another channel (in Cyan). We learned the rule that control the way this external element channel influences
the learnable channel(Yellow) and display the resulting behavior here. The moving agent is effectively attracted to this introduce component. By controlling
Expand Down Expand Up @@ -924,7 +924,7 @@ <h4> Qualitative </h4>
</div>

<p style="font-size: 19px;color:#000000;text-align:center;" >
Video S16: Robustness to initialization<br>
Video S18: Robustness to initialization<br>
<span style="font-size: 14px;color:#A0A0A0;">
Testing the generalization/robustness to initial patterns. We replace the learned initial pattern by : left a disk with a gradient; middle a large disk (much larger than an agent); right
right top a disk with gradient of another size, right bottom a disk without gradient. Some initialization lead to the robust emergence of one or several agents while some lead to the collapse of the pattern.
Expand Down Expand Up @@ -968,7 +968,7 @@ <h3> additional </h3>

</div>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video S17: Agent considered non moving by our moving test<br>
Video S19: Agent considered non moving by our moving test<br>
</p>
</div>

Expand All @@ -990,7 +990,7 @@ <h3> additional </h3>
<source src="public/unstable.mp4" type="video/mp4">
</video>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video SX: Unstability<br>
Video S20: Unstability<br>
<span style="font-size: 14px;color:#A0A0A0;">
Example of partial robustness of a moving agent. The agent is able to deal with some perturbation by obstacle but some other might break
the equilibrium (leading to explosion)
Expand All @@ -1004,7 +1004,7 @@ <h3> additional </h3>
<source src="public/kernels.mp4" type="video/mp4">
</video>
<p style="font-size: 19px;color:#000000;text-align:center;" >
Video SX: Visualization of each rule<br>
Video S21: Visualization of each rule<br>
<span style="font-size: 14px;color:#A0A0A0;">
For the visualization of the role of each rule, we display the growth (in the magma colormap) of each of the 10 rules in the exterior videos. The inner top video shows the normal simulation.
The inner bottom video displays the weighted sum of the growth of all the rules in grey level (1 being white and 0 being black), showing what is added to the current state of the learnable channel.
Expand Down
Loading

0 comments on commit a2736a6

Please sign in to comment.