Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation

Fernando Montes-Gonzalez

cs.ROOct 7, 2026

Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation

Authors: Fernando Montes-Gonzalez

Organizations: Instituto de Investigaciones en Inteligencia Artificial, Universidad Veracruzana, Mexico

Abstract

This work examines the transfer of a co-evolved communication mechanism between two robotic agents from a discrete two-dimensional (2D) simulator to a three-dimensional simulator with real physics (3D). The study focuses on whether a communication mechanism co-evolved in a 2D environment retains its functional role after transfer to a 3D physics-based simulator. To support this analysis, the effects of the episode time budget, the social cue, and the asymmetry between the two co-evolved roles were examined. The results indicate that the success rate increased approximately linearly with the evaluated time budgets, with no evidence of a plateau between 2,000 and 6,000 physics steps, suggesting that evaluations based on shorter episodes may underestimate the performance of the trained controllers. In both simulators, the social cue functioned primarily as a jam- assistance mechanism rather than as a navigation guide, although with a more pronounced effect in 2D. Analysis of eight independent evolutionary runs revealed a consistent direction of asymmetry, although its magnitude varied across runs. Controlling the processing order between agents allowed us to rule out an artifact of the physics engine. Finally, the results are discussed in terms of the factors that may contribute to the remaining performance gap observed after transfer.

Figures & tables

Panel of Figure 1 — Figure 1: Comparison of the simulation engines used for the evaluation of coevolved communication between robotic agents. (a) 2D engine with discrete environment representation, without physical modeling, used for low computational-cost simulations. (b) 3D engine based on PyBullet, with 240 Hz physical simulation and decoupled simulation time control through decision updates every 15 physics steps ( $\approx$ 16 Hz), equivalent to a control cycle commonly used in robotic simulators. Both environments contain two agents, shared obstacles, and shared objectives for performing cooperative tasks.

Figure 2: Distribution of the robot’s eight proximity sensors. The sensors are evenly spaced at 45 ∘ intervals around the robot, providing 360 ∘ detection coverage. The black line indicates the robot’s forward-facing direction and serves as a visual reference for interpreting sensor orientation in both the 2D and 3D simulators.

Figure 3: Success rate of agents A and B as a function of the episode time budget (2,000 to 6,000 physics steps) for checkpoint v15_full_final without retraining. Error bars represent 95% confidence intervals for a binomial proportion ( $n=300$ episodes per budget). The success rate increased for both agents as the time budget increased. Agent B maintained a higher success rate than agent A across all evaluated budgets.

Budget	With signal	Without signal	Difference	n	p
(steps)	(%)	(%)	(pp)	(with signal)
2,000	11.1	3.5	7.6	36	$0.146$
3,000	11.2	2.3	8.8	269	$<0.0001$
4,000	9.6	2.0	7.6	1,020	$<0.0001$
6,000	12.2	1.5	10.7	2,054	$<0.0001$

Table 1: Stall resolution rate with and without social signal, by episode time budget.

Figure 4: Stall resolution rate with social signal present (heard) and absent (silent), as a function of the episode time budget. Error bars show the 95% confidence interval for a binomial proportion, calculated from the counts observed in each condition. For the 2,000-step budget, the observed difference did not reach statistical significance, coinciding with the small number of decision points classified as stalled with a signal present ( $n=36$ ).

Figure 5: B/A weight ratios in the right_turn action column ( w_out and w_res ) for eight independent evolutionary runs (four in the 3D simulator and four in the 2D simulator). The horizontal dashed line indicates parity between agents (ratio = 1.0). The w_res ratio was significantly above parity ( $p=0.012$ ), whereas the w_out ratio showed the same trend without reaching conventional statistical significance ( $p=0.098$ ). The labels on the x-axis correspond to the original checkpoint names of the evolutionary runs and are retained for traceability.

Explore similar work

Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics
Sep 29, 2026Fernando Montes-GonzalezCo-Evolution Protocol
Universidad Veracruzana, Mexico
SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems
Jun 2, 2026Linyue Pan, Yaoming Zhu, Lin Qiu +2Self-Evolving Agents Self-Improving Agents
Tsinghua University, China · Meituan, China
Abstract Sim2Real through Approximate Information States
Apr 16, 2026Yunfu Deng, Yuhao Li, Josiah P. HannaSim-To-Real Reinforcement Learning Sim-To-Real Gap
Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI 53706 USA · Manning College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA 01003 USA

Sep 29, 2026, cs.ROJ/K move · Enter open · S save

Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics

Fernando Montes-Gonzalez

Universidad Veracruzana, Mexico

Co-Evolution Protocol Incomplete

Open paper AskPDF arXiv

This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots, controlled by a GRU network with residual connection, were evaluated in a food-seeking task with social signaling. The sensory and motor translation layer required three corrections for stable physical operation, including the calibration of a hunger term based on a measurable asymmetry in the trained residual weights. Even with these corrections, the transfer was partial and asymmetric: one agent reached the food source in one of thirty tested seeds, while the other did not reach it in any. Task success was measured by both agents reaching the food area. An additional experiment incorporating explicit directional information in the social channel produced observable changes in the trajectory of the receiving agent and improvements in several specific cases. However, these improvements were not enough to allow the second agent to reach the food source, suggesting that the limitation may not be explained solely by signal translation, but also by the ability to navigate under the new physical constraints. The results suggest that successful transfer of emergent communication may depend not only on preserving the signaling process itself, but also on preserving the ecological and navigational conditions under which the protocol evolved.

Abstract

Explore similar work

Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics

SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems

Abstract Sim2Real through Approximate Information States